BG2.5 | Integrating AI and advanced data analytics to improve soil carbon and greenhouse gas (GHG) predictions from different ecosystems
EDI
Integrating AI and advanced data analytics to improve soil carbon and greenhouse gas (GHG) predictions from different ecosystems
Convener: Bhaskar MitraECSECS | Co-conveners: Jagadeesh Yeluripati, Priscila Matos, Alina Premrov, Yushu Xia

Recent advancements in AI and the availability of big data through technologies like physical sensor networks and remote sensing are revolutionizing how we collect, process, and predict system dynamics. These emerging technologies have the potential to enable more accurate GHG (N2O, CH4, CO2) emission estimates and a better understanding of soil carbon dynamics across diverse ecosystems, which are crucial for achieving NetZero and tackling climate change. This session solicits papers that will explore various AI and machine learning approaches in conjunction with various data-driven inductive approaches such as causality analysis, time series modelling, and Bayesian statistics across space (point, landscape to region) and time (diurnal, weeks, seasons, inter-annual, and decadal).

We specifically encourage submissions that will provide a holistic view of AI-powered solutions for predicting ecosystem dynamics and guide policy decisions for effective climate mitigation and adaptation strategies (e.g., nature-based climate solutions).

Recent advancements in AI and the availability of big data through technologies like physical sensor networks and remote sensing are revolutionizing how we collect, process, and predict system dynamics. These emerging technologies have the potential to enable more accurate GHG (N2O, CH4, CO2) emission estimates and a better understanding of soil carbon dynamics across diverse ecosystems, which are crucial for achieving NetZero and tackling climate change. This session solicits papers that will explore various AI and machine learning approaches in conjunction with various data-driven inductive approaches such as causality analysis, time series modelling, and Bayesian statistics across space (point, landscape to region) and time (diurnal, weeks, seasons, inter-annual, and decadal).

We specifically encourage submissions that will provide a holistic view of AI-powered solutions for predicting ecosystem dynamics and guide policy decisions for effective climate mitigation and adaptation strategies (e.g., nature-based climate solutions).