Search

Earth system modelling (ESM) is essential for understanding past, present and future Earth processes. Deep learning (DL), with the data-driven strength of neural networks, has promise for improving ESM by exploiting information from Big Data. Yet existing hybrid ESMs largely have deep neural networks incorporated only during the initial stage of model development. In this Perspective, we examine progress in hybrid ESM, focusing on the Earth surface system, and propose a framework that integrates neural networks into ESM throughout the modelling lifecycle. In this framework, DL computing systems and ESM-related knowledge repositories are set up in a homogeneous computational environment. DL can infer unknown or missing information, feeding it back into the knowledge repositories, while the ESM-related knowledge can constrain inference results of the DL. By fostering collaboration between ESM-related knowledge and DL systems, adaptive guidance plans can be generated through question-answering mechanisms and recommendation functions. As users interact iteratively, the hybrid system deepens its understanding of their preferences, resulting in increasingly customized, scalable and accurate guidance plans for modelling Earth processes. The advancement of this framework necessitates interdisciplinary collaboration, focusing on explainable DL and maintaining observational data to ensure the reliability of simulations.

Este producto forma parte de una serie de infografías de divulgación científica que buscan reseñar algunas de las investigaciones más importantes en las que ha tenido participación la Universidad EAFIT, publicadas en las revistas especializadas más prestigiosas del mundo

Satellite-derived data provide important information about river characteristics such as channel geometry, water surface area, water levels, and floodplain extension (Rokni et al. 2015; Schumann and Moller 2015; Smith 1997)

River discharge data and magnitudes of floods are often not readily available for decision makers of many developing nations, including Colombia. And this while flooding for these regions is often devastating, causing many fatalities and insurmountable damage to the most vulnerable communities. During the we season, in strong La Nina years, infrastructural damages of over $US 7.2 billion have occurred. Mitigation of such natural disasters lacks data-supported scientific approaches for evaluating river response to extreme climate events. Here, we propose a satellite-based technique to measure river discharge at selected sites for the main northern Andean River, the Magdalena. This method has the advantage of back calculating daily river discharges over a period of two decades, and thus making it possible to calculate return intervals of significant flood events. The study shows that satellite based river discharges well capture a) the inter-annual variability of river discharge; b) the natural seasonality of water discharge along the floodplains; and c) peak discharges that were observed during La Nina conditions between 2008 and 2011. The last is likely more accurate compared to ground-based gauging stations, as ground-based stations tend to overflow during large flood events and as such are hampered to accurately monitor peak discharges. Furthermore, we show that these derived discharges can form the base to study river-floodplain connectivity, providing environmental decision makers with a technique that makes it possible to better monitor river and ecosystem processes.

Modeling is essential to characterize and explore complex societal and environmental issues in systematic and collaborative ways. Socio-environmental systems (SES) modeling integrates knowledge and perspectives into conceptual and computational tools that explicitly recognize how human decisions affect the environment. Depending on the modeling purpose, many SES modelers also realize that involvement of stakeholders and experts is fundamental to support social learning and decision-making processes for achieving improved environmental and social outcomes. The contribution of this paper lies in identifying and formulating grand challenges that need to be overcome to accelerate the development and adaptation of SES modeling. Eight challenges are delineated: bridging epistemologies across disciplines; multi-dimensional uncertainty assessment and management; scales and scaling issues; combining qualitative and quantitative methods and data; furthering the adoption and impacts of SES modeling on policy; capturing structural changes; representing human dimensions in SES; and leveraging new data types and sources. These challenges limit our ability to effectively use SES modeling to provide the knowledge and information essential for supporting decision making. Whereas some of these challenges are not unique to SES modeling and may be pervasive in other scientific fields, they still act as barriers as well as research opportunities for the SES modeling community. For each challenge, we outline basic steps that can be taken to surmount the underpinning barriers. Thus, the paper identifies priority research areas in SES modeling, chiefly related to progressing modeling products, processes and practices.

Modeling is essential to characterize and explore complex societal and environmental issues in systematic and collaborative ways. Socio-environmental systems (SES) modeling integrates knowledge and perspectives into conceptual and computational tools that explicitly recognize how human decisions affect the environment. Depending on the modeling purpose, many SES modelers also realize that involvement of stakeholders and experts is fundamental to support social learning and decision-making processes for achieving improved environmental and social outcomes. The contribution of this paper lies in identifying and formulating grand challenges that need to be overcome to accelerate the development and adaptation of SES modeling. Eight challenges are delineated: bridging epistemologies across disciplines; multi-dimensional uncertainty assessment and management; scales and scaling issues; combining qualitative and quantitative methods and data; furthering the adoption and impacts of SES modeling on policy; capturing structural changes; representing human dimensions in SES; and leveraging new data types and sources. These challenges limit our ability to effectively use SES modeling to provide the knowledge and information essential for supporting decision making. Whereas some of these challenges are not unique to SES modeling and may be pervasive in other scientific fields, they still act as barriers as well as research opportunities for the SES modeling community. For each challenge, we outline basic steps that can be taken to surmount the underpinning barriers. Thus, the paper identifies priority research areas in SES modeling, chiefly related to progressing modeling products, processes and practices.