iEMSs biennial conference
iEMSs biennial conference
This stream through its various sessions seeks to bring together academic experts, action researchers and practitioners to explore recent developments in participatory decision making, modelling, design and research to solve complex problems of today. We will focus on questions related to the latest trends in participatory research, what role AI and Machine Learning can play in advancing participatory methods, how to organise, support and promote stakeholder participation, as well as how diversity among stakeholder groups can help and related areas.
Environmental modelling of the environmental fate of a variety of contaminants in and across all environmental media is a powerful tool for regulatory and management strategies. Topics in this stream may cover aspects of modelling the chemical and physical transformation of pollutants in air, water and soil, the impact of pollution on human and ecosystem health, biodiversity and the integrated assessment of potential synergies and unintended consequences of technical, behavioural and nature-based solutions.
This stream will cover a range of approaches including open integrated system, and computational intelligence methods in environmental modeling, e.g., computational workflow development, data analytics, and hybrid models of AI and environmental informatics.
Modelling complex environmental and agricultural systems inevitably leads to a problem of the design or structure of the system and the identification of the “true values” of numerous parameters that affect model predictions. This stream will include topics related to the methods, tools, and applications in systems design, parameter identification, and evaluation of uncertainty of model predictions. We particularly welcome sessions and submissions that address the impact of a lack of knowledge about the systems design or parameters on likely outcomes in agricultural or environmental problems.
The stream will cover novel approaches to earth system modelling, software frameworks for predictions of complex interrelationships of environmental factors and their consequences for the planetary health. This includes approaches to simulation of human-environment interactions and integration of environmental and social determinants to assess risks to human health, quantitative and qualitative methods for sustainability assessment, and approaches to monitoring progress towards attainment of Sustainable Development Goals at the global, national, regional, and local levels.
Fast advances in remote sensing techniques, in-situ observation systems, and information and communication technologies have contributed to the proliferation of Big Data on environmental systems. Big Data brings about new opportunities for a better understanding of complex systems through new forms of information processing, storage, retrieval, and analytics. Machine learning, which refers to computer algorithms that automatically learn from data, can advance our prediction capability on complex systems with less human intervention. Collectively, Big Data and ML techniques have shown great potential for data-driven decision-making, operation research, and process optimization in planning and managing environmental systems. We encourage the submission of papers that provide insights into novel data solutions, software technologies, and computational and machine-learning methods to guide human activities on environmental systems, including, but not limited to, environmental systems planning, management, and operations.