Moxe empowers smarter, simpler, more secure data exchange for better healthcare

Moxe

Dissecting Video Games and If They Are Art: A Non-Gamer's Analysis

ভিডিও গেম ব্যবচ্ছেদ করা এবং সেগুলি যদি শিল্প হয়: একটি নন-গেমারের বিশ্লেষণ

Videospiele analysieren und ob sie Kunst sind: Die Analyse eines Nicht-Spielers

Diseccionando los videojuegos y si son arte: un análisis de un no jugador

Disséquer les jeux vidéo et s'ils sont de l'art : une analyse d'un non-joueur

विच्छेदित वीडियो गेम और यदि वे कला हैं: एक गैर-गेमर का विश्लेषण

ビデオ ゲームを解剖し、それがアートであるかどうか: 非ゲーマーによる分析

비디오 게임을 분석하고 그것이 예술이라면: 비게이머의 분석

Dissecando videogames e se eles são arte: uma análise de quem não é jogador

Анализ видеоигр и являются ли они искусством: анализ негеймера

Video Oyunlarını İncelemek ve Sanat Olup Olmadıklarını: Oyuncu Olmayan Bir Analiz

Phân tích trò chơi điện tử và liệu chúng có phải là nghệ thuật: Phân tích của một người không phải là game thủ

剖析视频游戏以及它们是否是艺术：非游戏玩家的分析

The good news of the , the European authority for anti-money laundering and countering terrorist financing, in Frankfurt, signals an expected change in the financial industry. is ready to collaborate with its members to ensure the financial crime fight has the means to be successful. establishment of AMLA The EU While this is just the start of more monitoring, AMLA will be operational in 2025, one thing is clear: customer mindsets are shifting towards a greater emphasis on technology and data management in financial crime prevention, according to , CEO of a Swedish regtech company. Gabriella Bussien Trapets, Bussien highlighted the importance of leveraging knowledge providers and in-house development, as well as stressing the need for banks to stay ahead through innovation and technology-driven solutions. Additionally, Bussien discussed the importance of educating customers about Know Your Customer (KYC) processes to avoid misunderstandings and mistrust. The AMLA driving factor The importance of the creation of AMLA is symptomatic of a specific moment.  Why has the EU decided to establish it now? What factors have led to this decision, and why wasn’t it created 10 or 20 years ago? Understanding the timing and rationale behind AMLA’s creation is crucial in grasping its significance in the fight against financial crime. For Bussien, the question arises as to why such measures haven’t been taken earlier. “However, when coordinating actions across multiple countries, there are inherent challenges in fostering willingness to collaborate. It seems that the recognition of the absolute necessity for such collaboration has matured over time. As the global landscape evolves, there’s a growing understanding that addressing financial crime requires a united, collaborative approach,” she said. She stresses the fact that within the EU, for instance, it’s increasingly apparent that ignoring these issues is no longer feasible. Thus, there’s a shift towards acknowledging the need for a comprehensive, collective response. “While debates may persist, it’s encouraging to see a realization emerging that significant action is warranted from both EU institutions and member states to address financial crime from a holistic perspective,” she added. It’s easy to think that this will be a pivotal moment for combating financial crime in Europe, but is it? What is clear is that this EU decision will establish a greater level of consistency and overarching supervision power, creating a more unified approach. From this perspective, added Bussien, it’s about ensuring stability and equality across the board within the EU financial system. This move towards centralized oversight aims to prevent fragmentation and promote a cohesive strategy in combating financial crime. The new financial rap From a customer perspective, there’s a renewed heightened awareness regarding financial institutions and their susceptibility to financial crimes, particularly in newer generations, who are accustomed to stringent KYC protocols and thorough background checks before becoming customers. For Trapets’ CEO, there’s a shift in expectations, akin to the emphasis on sustainability in business dealings. “Customers are increasingly discerning about where their money is invested, conducting extensive research before choosing a financial institution. This trend, observed especially among newer generations, signifies a departure from the past, where switching banks was less common due to digital barriers,” commented Bussien. The ease of digital banking has facilitated this shift, allowing customers to be more flexible in their choices. As a result, there’s a growing emphasis on informed decision-making and conscientious banking practices among consumers, particularly among younger generations. But, as Bussien said, regarding false positives and their impact on customer bank switching, it’s a complex issue. Reports, such as those in the , highlight instances of false positives leading to account closures by banks. “While these closures may occur due to system protocols rather than any illegal activity on the customer’s part, it still can lead to dissatisfaction, especially if one relies heavily on digital banking,” Bussien commented. “It’s crucial for banks to have robust KYC processes in place to minimize false positives and ensure knowledgeable staff capable of making informed decisions.” New York Times It seems clear that customers must understand that KYC questionnaires are linked to behavior analysis monitored by banks. Any inconsistencies between stated intentions and actual actions can prompt alerts. However, for Bussien, it’s equally important for banks to handle these situations delicately. Instead of immediately closing accounts, there should be thorough investigation processes in place to maintain customer satisfaction while upholding regulatory standards. Trust and credibility in the banking system It is debatable if recent news regarding alleged involvement in facilitating transactions for Iranian foreign entities can have significant repercussions on brand reputation and losing trust and credibility among customers and the broader community. “Generally speaking, loyalty to banks has evolved. Previously, people tended to remain loyal to the bank they initially chose, but this sentiment has shifted across generations. Nowadays, loyalty to a single bank is less common, indicating a broader trend of stretched loyalty,” mentioned Bussien. Lloyds Bank and Santander’s Regarding brand reputation, particularly in the financial sector, it’s unclear how much impact allegations of money laundering or similar issues have on customer churn. “While such scandals undoubtedly affect a bank’s image, customer behavior might be more influenced by their personal experiences. For instance, if a bank consistently fails to address fraudulent activities affecting customers, this may prompt individuals to switch banks, regardless of the institution’s involvement in larger-scale misconduct like money laundering,” added the Trapets CEO. In essence, according to the specialist, the triggers for changing banks might differ based on personal experiences with fraud prevention and customer service, as opposed to perceptions of the bank’s involvement in illicit activities. The role of tech in combating financial crime How to weigh the importance of technology in the banking industry’s efforts to combat financial crime? While some banks opt to develop solutions internally, it’s essential to recognize whether technology is truly their forte. Often, partnering with specialized technology providers proves more beneficial, as these entities possess the expertise and agility necessary for continuous innovation and compliance with regulations. Bussien makes it clear: “It’s a matter of weighing the bank’s internal capabilities against the advantages of leveraging external knowledge and resources. In most cases, banks may find it impractical and inefficient to handle such endeavors internally, given the complexities involved. Relying on technology providers ensures ongoing development and maintenance of robust systems tailored to evolving regulatory requirements.” It’s unmistakable that banks must prioritize the structuring and management of their data. Effective technology implementation hinges on having organized, accessible data sets. Without a structured approach to data management, even the most advanced technology solutions may falter. Therefore, alongside technological investments, banks must focus on refining their data infrastructure to maximize the effectiveness of anti-financial crime measures. All of this combined can foster the renewed importance of financial crime prevention in Europe.

The EU's New Anti-Money Laundering Authority and its Crime Prevention Focus

The TechBeat: Portfolio Management: All The Ways AI Is Transforming Modern Asset Strategies (5/3/2024)

The AI industry is dominated by discussions of massive LLMs like GPT-4, Claude 3, and Gemini. But there are equally big issues with relying on these closed-source LLMs. For one, you have minimal control. The models often worsen over time and exhibit biases that you can’t fix. Plus, the firms gatekeeping the models, from OpenAI to Anthropic to Google, can throttle your usage, increase your prices, or simply ban your account. If you run a business, you’re risking everything by using closed-source models. Another issue is their sheer size. They’re far too big and slow to be useful for hardware devices like portable assistants - something Rabbit and Humane AI learned only after scathing reviews. That’s where open-source, tiny LLM models come into play. The most accurate of these in the <2B parameter category is H2O.ai’s Danube 2. They’re becoming increasingly popular for deployment on edge devices, as traditional large language models are too computationally demanding to run efficiently on resource-constrained hardware. Tiny LLMs for phones Danube 2 is a “tiny LLM” that packs a surprising punch for its size. With just 1.8 billion parameters, Danube is lightweight compared to giants like GPT-4, but it achieves highly competitive performance across a wide range of natural language tasks. Trained on a carefully curated dataset of 2 trillion tokens from diverse web sources, Danube leverages techniques refined from models like Mistral to maximize its efficiency. Basically, you can download this model to your device and run it wherever you like — whether that’s new portable consumer hardware, a security camera, an IoT sensor, or anywhere else. One of the key advantages of Danube is its accessibility. With an Apache 2.0 license, it’s freely available for commercial use, lowering the barriers to entry for developers and businesses looking to incorporate AI into their mobile applications. H2O.ai has also released a fine-tuned version, Danube2–1.8B-Chat, specifically optimized for conversational AI. This could spur a wave of more natural and responsive chatbots and virtual assistants on devices from smartphones to smart home hubs. Tiny AI in healthcare The potential applications for small AI extend far beyond consumer-facing chatbots or phones. In the healthcare sector, companies like HeartSciences are leveraging compact machine learning models to supercharge the electrocardiogram (ECG). Heart disease is the leading cause of death globally, claiming around 51,000 lives each day, and ECGs are one of the primary tools for diagnosing cardiac issues. However, interpreting these readings requires specialized expertise that many healthcare providers lack, particularly in resource-constrained settings. HeartSciences’ MyoVista Wavelet ECG system aims to bridge this gap by incorporating sophisticated AI algorithms capable of spotting subtle patterns that human eyes might miss. Trained on vast datasets, these models act as an early warning system for cardiac dysfunction. Crucially, the machine learning behind MyoVista is designed to run efficiently on the kind of hardware you’d find in a typical doctor’s office or clinic, not a high-performance computing cluster. This is the essence of small AI — bringing the power of cutting-edge algorithms to the point of care, where they can have the greatest impact on patient outcomes. When minutes can mean the difference between life and death, having AI-powered insights available immediately is a game-changer. And with hundreds of millions of ECGs administered every year, the scalability of lightweight models like those used in MyoVista is key to making a real dent in the global burden of heart disease. Tiny AI for security Another promising application for small AI is in the realm of smart security systems. Traditional security cameras rely on motion detection and human monitoring to identify potential threats, leading to high rates of false alarms and missed incidents. However, by incorporating compact machine learning models, these systems can become much more intelligent and autonomous. Imagine a security camera equipped with an AI model trained to recognize not just motion but specific types of behaviors and objects. Such a system could distinguish between a person walking their dog and someone attempting to break into a building, alerting human operators only when there’s a genuine threat. By running these models directly on the camera hardware rather than streaming video to the cloud for analysis, smart security systems can operate more efficiently and protect sensitive data from potential breaches. Of course, developing effective AI models for smart security presents its own set of challenges. The models must be able to operate in real-time, processing video feeds as they come in while also being robust to variations in lighting, weather, and other environmental factors. They must also be trained on diverse datasets to avoid bias and ensure fair performance across different demographic groups. Despite these challenges, the potential benefits of AI-powered smart security are significant. By reducing false alarms and enabling proactive threat detection, these systems can help keep people and property safe while also reducing the workload on human operators. And as the underlying hardware continues to become more powerful and energy-efficient, the possibilities for edge-based AI in security applications will only continue to grow. Takeaways As the AI community continues to push the boundaries of what’s possible with large-scale models and infrastructure, it’s important not to lose sight of the transformative potential of small AI. By bringing powerful capabilities to the devices and contexts where they’re needed most, compact models have the potential to democratize access to AI’s benefits and touch billions of lives in meaningful ways. From the smartphones in our pockets to the medical devices in our clinics to the security cameras watching over our streets, small AI is poised to make a big impact. As we work to overcome the challenges around data, privacy, and bias, we must also recognize and celebrate the quiet revolution that’s happening at the edge. The future of AI may be small, but its potential is enormous. The AI industry is dominated by discussions of massive LLMs like GPT-4, Claude 3, and Gemini. But there are equally big issues with relying on these closed-source LLMs. For one, you have minimal control. The models often worsen over time and exhibit biases that you can’t fix. worsen over time exhibit biases Plus, the firms gatekeeping the models, from OpenAI to Anthropic to Google, can throttle your usage, increase your prices, or simply ban your account. If you run a business, you’re risking everything by using closed-source models. Another issue is their sheer size. They’re far too big and slow to be useful for hardware devices like portable assistants - something Rabbit and Humane AI learned only after scathing reviews . scathing reviews That’s where open-source, tiny LLM models come into play. The most accurate of these in the <2B parameter category is H2O.ai’s Danube 2 . They’re becoming increasingly popular for deployment on edge devices, as traditional large language models are too computationally demanding to run efficiently on resource-constrained hardware. H2O.ai’s Danube 2 Tiny LLMs for phones Danube 2 is a “tiny LLM” that packs a surprising punch for its size. With just 1.8 billion parameters, Danube is lightweight compared to giants like GPT-4, but it achieves highly competitive performance across a wide range of natural language tasks. Trained on a carefully curated dataset of 2 trillion tokens from diverse web sources, Danube leverages techniques refined from models like Mistral to maximize its efficiency. Basically, you can download this model to your device and run it wherever you like — whether that’s new portable consumer hardware, a security camera, an IoT sensor, or anywhere else. One of the key advantages of Danube is its accessibility. With an Apache 2.0 license, it’s freely available for commercial use, lowering the barriers to entry for developers and businesses looking to incorporate AI into their mobile applications. H2O.ai has also released a fine-tuned version, Danube2–1.8B-Chat , specifically optimized for conversational AI. This could spur a wave of more natural and responsive chatbots and virtual assistants on devices from smartphones to smart home hubs. Danube2–1.8B-Chat Tiny AI in healthcare The potential applications for small AI extend far beyond consumer-facing chatbots or phones. In the healthcare sector, companies like HeartSciences are leveraging compact machine learning models to supercharge the electrocardiogram (ECG). HeartSciences Heart disease is the leading cause of death globally, claiming around 51,000 lives each day, and ECGs are one of the primary tools for diagnosing cardiac issues. However, interpreting these readings requires specialized expertise that many healthcare providers lack, particularly in resource-constrained settings. HeartSciences’ MyoVista Wavelet ECG system aims to bridge this gap by incorporating sophisticated AI algorithms capable of spotting subtle patterns that human eyes might miss. Trained on vast datasets, these models act as an early warning system for cardiac dysfunction. Crucially, the machine learning behind MyoVista is designed to run efficiently on the kind of hardware you’d find in a typical doctor’s office or clinic, not a high-performance computing cluster. This is the essence of small AI — bringing the power of cutting-edge algorithms to the point of care, where they can have the greatest impact on patient outcomes. When minutes can mean the difference between life and death, having AI-powered insights available immediately is a game-changer. And with hundreds of millions of ECGs administered every year, the scalability of lightweight models like those used in MyoVista is key to making a real dent in the global burden of heart disease. Tiny AI for security Another promising application for small AI is in the realm of smart security systems . Traditional security cameras rely on motion detection and human monitoring to identify potential threats, leading to high rates of false alarms and missed incidents. However, by incorporating compact machine learning models, these systems can become much more intelligent and autonomous. smart security systems Imagine a security camera equipped with an AI model trained to recognize not just motion but specific types of behaviors and objects. Such a system could distinguish between a person walking their dog and someone attempting to break into a building, alerting human operators only when there’s a genuine threat. By running these models directly on the camera hardware rather than streaming video to the cloud for analysis, smart security systems can operate more efficiently and protect sensitive data from potential breaches. Of course, developing effective AI models for smart security presents its own set of challenges. The models must be able to operate in real-time, processing video feeds as they come in while also being robust to variations in lighting, weather, and other environmental factors. They must also be trained on diverse datasets to avoid bias and ensure fair performance across different demographic groups. Despite these challenges, the potential benefits of AI-powered smart security are significant. By reducing false alarms and enabling proactive threat detection, these systems can help keep people and property safe while also reducing the workload on human operators. And as the underlying hardware continues to become more powerful and energy-efficient, the possibilities for edge-based AI in security applications will only continue to grow. Takeaways As the AI community continues to push the boundaries of what’s possible with large-scale models and infrastructure, it’s important not to lose sight of the transformative potential of small AI. By bringing powerful capabilities to the devices and contexts where they’re needed most, compact models have the potential to democratize access to AI’s benefits and touch billions of lives in meaningful ways. From the smartphones in our pockets to the medical devices in our clinics to the security cameras watching over our streets, small AI is poised to make a big impact. As we work to overcome the challenges around data, privacy, and bias, we must also recognize and celebrate the quiet revolution that’s happening at the edge. The future of AI may be small, but its potential is enormous.

Danube-2: The Tiny AI Model Leading the Open LLM Leaderboard

Authors: (1) Renato P. dos Santos, CIAGE – Centre for Generative Artificial Intelligence in Cognition and Education. Table of Links Abstract and Introduction Materials And Methods Results and Analyses Prompts and generated texts Conceptualizing chemical reactions Deepening on understanding of chemical reactions Question about combustion Question about a graph of gases turning into water over time Question about the difference between atoms, molecules, and moles Deepening on the concept of mole Question about changing of state Question about an animated representation of water molecules undergoing phase changes Question about plasma, a state of matter Question about chemical bondings Question about illustration of chemical bonds Question about the essence of the type of chemical bonding Further analysis Conclusions Limitations of the study and possible future studies Author Contributions, Conflicts of interest, Acknowledgements, and References Conclusions In our study evaluating the proficiency of four AI language models—ChatGPT, Bing Chat, Bard, and Claude—in elucidating chemistry concepts, ChatGPT stood out, decisively surpassing Bing Chat's performance. Bard and Claude trailed closely, with all three showcasing a more in- depth, precise, and nuanced understanding, underscoring ChatGPT's adeptness at contextual comprehension. Our findings highlight the robustness of GenAIbots like ChatGPT, Bing Chat, Bard, and Claude as agents-to-think-with in Chemistry education. These AI models seem suitable to offer interactivity, customisation, and multidisciplinary knowledge and promote critical thinking, problem-solving, creativity, and collaboration. They facilitate dynamic conversations and tailored content in Chemistry and potentially other domains. Engaging with GenAIbots might enhance critical thinking, problem-solving, and creativity, fostering collaborative discussions and projects in group settings and deepening understanding of the topics. By integrating GenAIbots into Chemistry education, we're aligning with the principles of Papert's Constructionism. This theory posits that learning is most effective when students actively construct knowledge by creating tangible representations in meaningful contexts. This approach encourages students to engage deeply, fostering their problem-solving, critical thinking, and creative skills. This paper is under CC BY-SA 4.0 DEED license. available on arxiv

ChatGPT Leads the Pack: AI Language Models Elevating Chemistry Education

RAND Suggests Metaverses Could Operate as Modern Societal States

RAND পরামর্শ দেয় মেটাভার্স আধুনিক সামাজিক রাষ্ট্র হিসাবে কাজ করতে পারে

RAND schlägt vor, Metaversen könnten als moderne Gesellschaftsstaaten funktionieren

RAND sugiere que los metaversos podrían funcionar como estados sociales modernos

RAND suggère que les métavers pourraient fonctionner comme des États sociétaux modernes

RAND का सुझाव है कि मेटावर्स आधुनिक सामाजिक राज्यों के रूप में काम कर सकते हैं

RANDはメタバースが現代の社会国家として機能する可能性を示唆

RAND는 메타버스가 현대 사회 국가로 작동할 수 있다고 제안합니다.

RAND sugere que metaversos poderiam operar como estados sociais modernos

RAND предполагает, что метавселенные могут функционировать как современные социальные состояния

RAND, Meta Veri Dizilerinin Modern Toplumsal Durumlar Olarak İşleyebileceğini Öneriyor

RAND đề xuất Metaverses có thể hoạt động như các quốc gia xã hội hiện đại

兰德公司认为元宇宙可以像现代社会国家一样运作

This paper is available on arxiv under CC BY-SA 4.0 DEED license.
Authors:
(1) Lana L. Blaschke, Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, Potsdam Institute for Climate Impact Research, Potsdam, Germany and lana.blaschke@pik-potsdam.de;
(2) Da Nian, Potsdam Institute for Climate Impact Research, Potsdam, Germany;
(3) Sebastian Bathiany,  Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, and Potsdam Institute for Climate Impact Research, Potsdam, Germany;
(4)  Maya Ben-Yami,  Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, and Potsdam Institute for Climate Impact Research, Potsdam, Germany;
(5) Taylor Smith, Institute of Geosciences, University of Potsdam, 14476 Potsdam, Germany;
(6)  Chris A. Boulton, Global Systems Institute, University of Exeter, EX4 4QE Exeter, UK ;
(7) Niklas Boers, Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, Potsdam Institute for Climate Impact Research, Potsdam, Germany, Global Systems Institute, University of Exeter, EX4 4QE Exeter, UK, and Department of Mathematics, University of Exeter, EX4 4QF Exeter, UK. Table of Links Abstract and Introduction
Materials and Methods
Data
Results
Conclusions, Open Research Section and Conflict of Interest/Competing Interests
Author Contributions, Supplementary Information, Acknowledgments and References
Additional Insight from the Conceptual Model 
AMSR2 until 2022 Excluded Due to Missing Human Land Use Data
Investigation of Resilience Loss in AMSR2’s X-Band
Results Proving Robustness
Potential Driving Forces and Sources of Bias ADDITIONAL INSIGHT FROM THE CONCEPTUAL MODEL Text S1. Stability in the conceptual model The interaction of vegetation and precipitation is plotted in Figure S1. In the conceputal model, vegetation is a function of absolute incoming precipitation only and is not dependent on the cell’s location. Hence, it is the same for each cell and plotted as the single black solid line. Precipitation on the other hand is a function of the vegetation of the cell, but also of the vegetation of the cell’s eastern neighbors. Hence, it differs for all cells, which are encoded by the colors as in Figure 2. For the calculation of one cell’s precipitation as a function of vegetation, its eastern neighbors are considered to be in equilibrium. Furthermore, precipitation depends on the amount of moisture coming in from the Atlantic ocean, or in other words on the control parameter B. The solid lines represent the state in the beginning of the experiment with B = 1010, and the dashed lines in the end with B = 990. Where the black and coloured lines cross at some (V∗, P∗), the corresponding value of vegetation supports the value of precipitation P∗, but also is V∗ supported by P∗. Hence, this point is considered a fixed point, or equilibrium. As the moisture inflow is reduced in the simulations from 1010 (solid lines) to 990 (dashed lines), the fixed points with high vegetation values vanish, explaining the tipping in the Figures S4 and S5 . Text S2. Precipitation decrease in the conceptual model The results of simulations with decreasing moisture inflow from the Atlantic ocean (decreasing B(t)) were presented in the main text in Figure 4. Figure S2 zooms in into cell-wise total precipitation and highlights its stochasticity as well as the almost linear decrease up to the Tipping Point of vegetation. Text S3. Deforestation scenario leads to Tipping in the conceptual model The results of simulations with decreasing moisture inflow from the Atlantic ocean (decreasingB(t)) were presented in the main text in Figure 4. Figure S3 is identical but presents the results from simulations with unchanging inflow from the Atlantic, i.e. B(t) = 1000 for all t. Instead, the amount vegetation in the east-most cell is considered the bifurcation parameter and constantly decreased from 1 to 0, thereby mimicking deforestation. Text S4. Distribution of the trends for the three resilience indicators In the conceptual model, all indicators show clear trends when approaching the Tipping Point of vegetation, as illustrated in Figure S4. There, clearly all three indicators show a strong shift towards positive values with only very few negative ones for AC1. In a spatially extended system like the ARF, one would thus expect all three indicators to increase when the corresponding grid cell loses resilience. Text S5. Distribution of the trends for the three resilience indicators In Figure 4 the time of emergence (ToE) was defined as the first time when a trend becomes significant. Yet, as more conservative approach one can define the ToE as the time when a trend becomes permanently significant, i.e. when all trends later in time are significant as well. The results with this definition are displayed in Figure S5. The uncertainty in the timing of this type of ToE differs much less for AC1 compared to the definition in the main text. This indicates that AC1 might be more prone to false alarms. This paper is available on arxiv under CC BY-SA 4.0 DEED license. Authors: (1) Lana L. Blaschke, Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, Potsdam Institute for Climate Impact Research, Potsdam, Germany and lana.blaschke@pik-potsdam.de; (2) Da Nian, Potsdam Institute for Climate Impact Research, Potsdam, Germany; (3) Sebastian Bathiany,  Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, and Potsdam Institute for Climate Impact Research, Potsdam, Germany; (4)  Maya Ben-Yami,  Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, and Potsdam Institute for Climate Impact Research, Potsdam, Germany; (5) Taylor Smith, Institute of Geosciences, University of Potsdam, 14476 Potsdam, Germany; (6)  Chris A. Boulton, Global Systems Institute, University of Exeter, EX4 4QE Exeter, UK ; (7) Niklas Boers, Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, Potsdam Institute for Climate Impact Research, Potsdam, Germany, Global Systems Institute, University of Exeter, EX4 4QE Exeter, UK, and Department of Mathematics, University of Exeter, EX4 4QF Exeter, UK. This paper is available on arxiv under CC BY-SA 4.0 DEED license. Authors: Authors: (1) Lana L. Blaschke, Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, Potsdam Institute for Climate Impact Research, Potsdam, Germany and lana.blaschke@pik-potsdam.de; (2) Da Nian, Potsdam Institute for Climate Impact Research, Potsdam, Germany; (3) Sebastian Bathiany,  Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, and Potsdam Institute for Climate Impact Research, Potsdam, Germany; (4)  Maya Ben-Yami,  Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, and Potsdam Institute for Climate Impact Research, Potsdam, Germany; (5) Taylor Smith, Institute of Geosciences, University of Potsdam, 14476 Potsdam, Germany; (6)  Chris A. Boulton, Global Systems Institute, University of Exeter, EX4 4QE Exeter, UK ; (7) Niklas Boers, Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany, Potsdam Institute for Climate Impact Research, Potsdam, Germany, Global Systems Institute, University of Exeter, EX4 4QE Exeter, UK, and Department of Mathematics, University of Exeter, EX4 4QF Exeter, UK. Table of Links Abstract and Introduction Materials and Methods Data Results Conclusions, Open Research Section and Conflict of Interest/Competing Interests Author Contributions, Supplementary Information, Acknowledgments and References Additional Insight from the Conceptual Model AMSR2 until 2022 Excluded Due to Missing Human Land Use Data Investigation of Resilience Loss in AMSR2’s X-Band Results Proving Robustness Potential Driving Forces and Sources of Bias Abstract and Introduction Abstract and Introduction Materials and Methods Materials and Methods Data Data Results Results Conclusions, Open Research Section and Conflict of Interest/Competing Interests Conclusions, Open Research Section and Conflict of Interest/Competing Interests Author Contributions, Supplementary Information, Acknowledgments and References Author Contributions, Supplementary Information, Acknowledgments and References Additional Insight from the Conceptual Model Additional Insight from the Conceptual Model AMSR2 until 2022 Excluded Due to Missing Human Land Use Data AMSR2 until 2022 Excluded Due to Missing Human Land Use Data Investigation of Resilience Loss in AMSR2’s X-Band Investigation of Resilience Loss in AMSR2’s X-Band Results Proving Robustness Results Proving Robustness Potential Driving Forces and Sources of Bias Potential Driving Forces and Sources of Bias ADDITIONAL INSIGHT FROM THE CONCEPTUAL MODEL Text S1. Stability in the conceptual model The interaction of vegetation and precipitation is plotted in Figure S1. In the conceputal model, vegetation is a function of absolute incoming precipitation only and is not dependent on the cell’s location. Hence, it is the same for each cell and plotted as the single black solid line. Precipitation on the other hand is a function of the vegetation of the cell, but also of the vegetation of the cell’s eastern neighbors. Hence, it differs for all cells, which are encoded by the colors as in Figure 2. For the calculation of one cell’s precipitation as a function of vegetation, its eastern neighbors are considered to be in equilibrium. Furthermore, precipitation depends on the amount of moisture coming in from the Atlantic ocean, or in other words on the control parameter B. The solid lines represent the state in the beginning of the experiment with B = 1010, and the dashed lines in the end with B = 990. Where the black and coloured lines cross at some (V∗, P∗), the corresponding value of vegetation supports the value of precipitation P∗, but also is V∗ supported by P∗. Hence, this point is considered a fixed point, or equilibrium. As the moisture inflow is reduced in the simulations from 1010 (solid lines) to 990 (dashed lines), the fixed points with high vegetation values vanish, explaining the tipping in the Figures S4 and S5 . Text S2. Precipitation decrease in the conceptual model The results of simulations with decreasing moisture inflow from the Atlantic ocean (decreasing B(t)) were presented in the main text in Figure 4. Figure S2 zooms in into cell-wise total precipitation and highlights its stochasticity as well as the almost linear decrease up to the Tipping Point of vegetation. Text S3. Deforestation scenario leads to Tipping in the conceptual model The results of simulations with decreasing moisture inflow from the Atlantic ocean (decreasingB(t)) were presented in the main text in Figure 4. Figure S3 is identical but presents the results from simulations with unchanging inflow from the Atlantic, i.e. B(t) = 1000 for all t. Instead, the amount vegetation in the east-most cell is considered the bifurcation parameter and constantly decreased from 1 to 0, thereby mimicking deforestation. Text S4. Distribution of the trends for the three resilience indicators In the conceptual model, all indicators show clear trends when approaching the Tipping Point of vegetation, as illustrated in Figure S4. There, clearly all three indicators show a strong shift towards positive values with only very few negative ones for AC1. In a spatially extended system like the ARF, one would thus expect all three indicators to increase when the corresponding grid cell loses resilience. Text S5. Distribution of the trends for the three resilience indicators In Figure 4 the time of emergence (ToE) was defined as the first time when a trend becomes significant. Yet, as more conservative approach one can define the ToE as the time when a trend becomes permanently significant, i.e. when all trends later in time are significant as well. The results with this definition are displayed in Figure S5. The uncertainty in the timing of this type of ToE differs much less for AC1 compared to the definition in the main text. This indicates that AC1 might be more prone to false alarms.

Loss of Amazon Rainforest Resilience: Additional Insight from the Conceptual Model

Population Stability Index (PSI) is a statistical measure commonly used in credit risk modeling and other fields to assess the stability of a population across different time periods or segments. It's particularly valuable in scenarios where changes in the population distribution could impact the effectiveness of a model. It is a fundamental assumption that the population on which a statistical model is applied to is similar to the population on which the model is developed at. The model performance relies on the closeness between the model development sample and the production data. Therefore, there is an intrinsic need to compare the two samples (development vs production) and assess whether a model needs to be recalibrated. The population change may occur for several reasons – change in the business strategies and policies or changes in external factors such as the political, economic and social environment. The model performance is impacted because of a change in the joint distribution p(y, X), where y is the model outcome and X is the design matrix that comprises the observations of the model features. Therefore, the entire model fit, i.e., the estimates of the model coefficients and the inherent functions get impacted. If this happens, then a decision must be made towards the recalibration or redevelopment of the model.  Before we dive deep into the PSI mathematical expression, we start with some key concepts on Entropy and KL divergence. Entropy and KL Divergence Entropy is a measure of uncertainty or randomness in a set of data. In machine learning, particularly in decision trees and information theory, entropy is used to quantify the impurity or disorder in a dataset. For instance, the splits of a decision tree for a classification problem are created to minimize the entropy. Entropy is used to determine the best attribute to split the data at each node of the decision tree. In the above definition of entropy, the negative sign ensures that Entropy is positive (because log of the probability will be negative as the probability will be < 1). Higher (lower) the value of P(X = X_i) lower (higher) is the entropy or randomness or uncertainty about X. Thus, ‘skewed’ distributions have lower entropy but ‘balanced’ distributions have higher entropy. The objective of splitting a variable at a node for a binary classification problem is to create more skewed distribution such that we can discriminate between an outcome value y = 1 and outcome value y = 0. Therefore, we move from a high entropy stage before splitting the variable to a lower entropy stage after splitting the variable.
If Entropy H(X) is high, then the uncertainty before knowing X is high. So after knowing X we have gained more information.
If Entropy H(X) is low, then the uncertainty before knowing X is low. So after knowing X we have gained less information.
We try to minimize entropy whilst building binary regression models. For example, we ‘bin’ or ‘discretize’ a model factor such the distribution of binary outcome becomes as skewed as possible across the different bins. Kullback-Liebler Divergence (KL Divergence) has been referred in several places in the literature (Lin, 2017), (Wu & Olson, 2010), (Li et al., 2008), etc. It measures the difference between two probability distributions p(x) and q(x). It quantifies how one probability distribution diverges from another. The distribution p(x) is considered the ‘true’ or ‘base’ distribution, and the distribution q(x) is considered the ‘untrue’ or ‘target’ distribution, so that KL Divergence represents some sort of loss due to using the ‘wrong’ distribution. KL divergence is non-negative and is zero if and only if p(x) and q(x) are identical, i.e., the same distribution. KL divergence measures the dissimilarity of the two probability distributions p(x) and q(x). If both the distributions are identical, KL Divergence is 0. We have a single random variable “X” and we have two different probability distributions for that variable. One is assumed to be the ‘true’ distribution and the other is the approximation of the ‘true’ distribution. So, we try “approximating” one distribution with the other and calculate the difference in the information about the event as a measure of the “divergence”. Note that the notation ‘P||Q’ implies P is approximated as Q.
Notice how the mathematical expressions for the individual terms of KL divergence are similar to that of Entropy or information which we introduced earlier. The second term inside the brackets is the information in p(x) about x. The first term inside the brackets is the information in an approximation distribution of p(x) as q(x) about x. That is if we approximate the target distribution p(x) by q(x); then the difference in the information between them is the relative entropy or KL Divergence index. The better our approximation the closer p(x) and q(x) and hence the KL divergence will be 0.
Even though KL Divergence measures divergence of q(x) from p(x), it is technically not a distance measure because the definition is not symmetric. Thus KL(P||Q) != KL(Q||P) Population Stability Index – Now that we have covered the mathematical expressions of Entropy and KL Divergence Index, we will see how they would help us in understanding the expression of Population Stability Index. Notice that we have added another term q(x) inside the brackets of KL divergence expression to get the mathematical expression for PSI. But the formulae look so similar that we can think of expressing PSI as a function of KL Divergence. Here is how we can do that. That is the PSI metric is actually the sum of the relative entropies of q(x) over p(x) and p(x) over q(x). In other words we are adding the information ‘gain’ by expressing p(x) using an approximation q(x) and vice-versa. The reason we do this is because we don’t know the ‘ground truth’. We assume that one of them is a ‘true’ distribution and the other is an ‘approximation’; and as we know that the KL divergence is not symmetric, we compute it from p(x) to q(x) and vice-versa and add them to get a final metric which can be judged to ascertain the difference between p(x) and q(x). The PSI calculation typically begins by dividing the data into bins or segments based on key variables used in the model.
PSI values close to zero indicate stability between the initial and new populations.
Higher PSI values suggest significant shifts in the population distribution, which may require further investigation or model recalibration. So how high should PSI be to make that judgement? The following table summarizes the PSI values which are ‘industry wide rules of thumb’. Interestingly, PSI is very similar to ‘Information Value’ used to measure the strength of the modelling variables in developing credit risk models. We will explore that soon in a different article. Population Stability Index (PSI) is a statistical measure commonly used in credit risk modeling and other fields to assess the stability of a population across different time periods or segments. It's particularly valuable in scenarios where changes in the population distribution could impact the effectiveness of a model. It is a fundamental assumption that the population on which a statistical model is applied to is similar to the population on which the model is developed at. The model performance relies on the closeness between the model development sample and the production data. Therefore, there is an intrinsic need to compare the two samples (development vs production) and assess whether a model needs to be recalibrated. The population change may occur for several reasons – change in the business strategies and policies or changes in external factors such as the political, economic and social environment. The model performance is impacted because of a change in the joint distribution p(y, X ), where y is the model outcome and X is the design matrix that comprises the observations of the model features. Therefore, the entire model fit, i.e., the estimates of the model coefficients and the inherent functions get impacted. If this happens, then a decision must be made towards the recalibration or redevelopment of the model.  Before we dive deep into the PSI mathematical expression, we start with some key concepts on Entropy and KL divergence. X Entropy and KL Divergence Entropy and KL Divergence Entropy and KL Divergence Entropy is a measure of uncertainty or randomness in a set of data. In machine learning, particularly in decision trees and information theory, entropy is used to quantify the impurity or disorder in a dataset. For instance, the splits of a decision tree for a classification problem are created to minimize the entropy. Entropy is used to determine the best attribute to split the data at each node of the decision tree. In the above definition of entropy, the negative sign ensures that Entropy is positive (because log of the probability will be negative as the probability will be < 1). Higher (lower) the value of P(X = X_i) lower (higher) is the entropy or randomness or uncertainty about X. Thus, ‘skewed’ distributions have lower entropy but ‘balanced’ distributions have higher entropy. The objective of splitting a variable at a node for a binary classification problem is to create more skewed distribution such that we can discriminate between an outcome value y = 1 and outcome value y = 0. Therefore, we move from a high entropy stage before splitting the variable to a lower entropy stage after splitting the variable. If Entropy H(X) is high, then the uncertainty before knowing X is high. So after knowing X we have gained more information. If Entropy H(X) is low, then the uncertainty before knowing X is low. So after knowing X we have gained less information. We try to minimize entropy whilst building binary regression models. For example, we ‘bin’ or ‘discretize’ a model factor such the distribution of binary outcome becomes as skewed as possible across the different bins. Higher (lower) the value of P(X = X_i) lower (higher) is the entropy or randomness or uncertainty about X. Thus, ‘skewed’ distributions have lower entropy but ‘balanced’ distributions have higher entropy. The objective of splitting a variable at a node for a binary classification problem is to create more skewed distribution such that we can discriminate between an outcome value y = 1 and outcome value y = 0. Therefore, we move from a high entropy stage before splitting the variable to a lower entropy stage after splitting the variable. If Entropy H(X) is high, then the uncertainty before knowing X is high. So after knowing X we have gained more information. If Entropy H(X) is low, then the uncertainty before knowing X is low. So after knowing X we have gained less information. We try to minimize entropy whilst building binary regression models. For example, we ‘bin’ or ‘discretize’ a model factor such the distribution of binary outcome becomes as skewed as possible across the different bins. Kullback-Liebler Divergence (KL Divergence) has been referred in several places in the literature (Lin, 2017), (Wu & Olson, 2010), (Li et al., 2008), etc. It measures the difference between two probability distributions p(x) and q(x). It quantifies how one probability distribution diverges from another. The distribution p(x) is considered the ‘true’ or ‘base’ distribution, and the distribution q(x) is considered the ‘untrue’ or ‘target’ distribution, so that KL Divergence represents some sort of loss due to using the ‘wrong’ distribution. KL divergence is non-negative and is zero if and only if p(x) and q(x) are identical, i.e., the same distribution. KL divergence measures the dissimilarity of the two probability distributions p(x) and q(x). If both the distributions are identical, KL Divergence is 0. We have a single random variable “X” and we have two different probability distributions for that variable. One is assumed to be the ‘true’ distribution and the other is the approximation of the ‘true’ distribution. So, we try “approximating” one distribution with the other and calculate the difference in the information about the event as a measure of the “divergence”. Note that the notation ‘P||Q’ implies P is approximated as Q. Notice how the mathematical expressions for the individual terms of KL divergence are similar to that of Entropy or information which we introduced earlier. The second term inside the brackets is the information in p(x) about x. The first term inside the brackets is the information in an approximation distribution of p(x) as q(x) about x. That is if we approximate the target distribution p(x) by q(x); then the difference in the information between them is the relative entropy or KL Divergence index. The better our approximation the closer p(x) and q(x) and hence the KL divergence will be 0. Even though KL Divergence measures divergence of q(x) from p(x), it is technically not a distance measure because the definition is not symmetric. Thus KL(P||Q) != KL(Q||P) We have a single random variable “X” and we have two different probability distributions for that variable. One is assumed to be the ‘true’ distribution and the other is the approximation of the ‘true’ distribution. So, we try “approximating” one distribution with the other and calculate the difference in the information about the event as a measure of the “divergence”. Note that the notation ‘P||Q’ implies P is approximated as Q. Notice how the mathematical expressions for the individual terms of KL divergence are similar to that of Entropy or information which we introduced earlier. The second term inside the brackets is the information in p(x) about x. The first term inside the brackets is the information in an approximation distribution of p(x) as q(x) about x. That is if we approximate the target distribution p(x) by q(x); then the difference in the information between them is the relative entropy or KL Divergence index. The better our approximation the closer p(x) and q(x) and hence the KL divergence will be 0. Even though KL Divergence measures divergence of q(x) from p(x), it is technically not a distance measure because the definition is not symmetric. Thus KL(P||Q) != KL(Q||P) Population Stability Index – Population Stability Index Population Stability Index Now that we have covered the mathematical expressions of Entropy and KL Divergence Index, we will see how they would help us in understanding the expression of Population Stability Index. Notice that we have added another term q(x) inside the brackets of KL divergence expression to get the mathematical expression for PSI. But the formulae look so similar that we can think of expressing PSI as a function of KL Divergence. Here is how we can do that. That is the PSI metric is actually the sum of the relative entropies of q(x) over p(x) and p(x) over q(x). In other words we are adding the information ‘gain’ by expressing p(x) using an approximation q(x) and vice-versa. The reason we do this is because we don’t know the ‘ground truth’. We assume that one of them is a ‘true’ distribution and the other is an ‘approximation’; and as we know that the KL divergence is not symmetric, we compute it from p(x) to q(x) and vice-versa and add them to get a final metric which can be judged to ascertain the difference between p(x) and q(x). The PSI calculation typically begins by dividing the data into bins or segments based on key variables used in the model. PSI values close to zero indicate stability between the initial and new populations. Higher PSI values suggest significant shifts in the population distribution, which may require further investigation or model recalibration. The PSI calculation typically begins by dividing the data into bins or segments based on key variables used in the model. PSI values close to zero indicate stability between the initial and new populations. Higher PSI values suggest significant shifts in the population distribution, which may require further investigation or model recalibration. So how high should PSI be to make that judgement? The following table summarizes the PSI values which are ‘industry wide rules of thumb’. Interestingly, PSI is very similar to ‘Information Value’ used to measure the strength of the modelling variables in developing credit risk models. We will explore that soon in a different article.

Population Stability Index in Machine learning models

MOXE

moxehealth.com

-- employees

Since n.d.

COMPANY RANKING

MOXE

EVERGREEN INDEX #6436

Representing this company? Click here to claim and customize this page!

Moxe WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!

MOXE

moxehealth.com

-- employees

Since n.d.

COMPANY RANKING

MOXE

EVERGREEN INDEX #6436

RELATED COMPANIESRANK

STORIES ABOUT MOXE

Representing this company? Click here to claim and customize this page!

Moxe WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!