Skip to main content

Optimisation of Agricultural Management for Soil Carbon Sequestration Using Deep Reinforcement Learning and Large-Scale Simulations

Objective
Soil carbon sequestration in croplands has tremendous potential to help mitigate climate change; however, it is challenging to develop optimal management practices to maximise the sequestered carbon and crop yield. This project aims to develop an intelligent agricultural management system using deep reinforcement learning (RL) and large-scale soil and crop simulations. To achieve this, we propose to build a simulator to model and simulate the complex soil-water-plant-atmosphere interactions, which will run on high-performance computing platforms.

Background
Massive simulations using such platforms allow the evaluation of the effects of various management practices under different weather and soil conditions in a timely and cost-effective manner. By formulating the management decision as an RL problem, we can leverage the state-of-the-art algorithms to train management policies, which are expected to maximise the stored organic carbon while maximising the crop yield. The whole system will be tested using data on soil and crops in both the mid-west of the United States and the Mediterranean region. The proposed research has great potential to impact climate change and food security, two of humanity’s most significant challenges.

Crossdisciplinary collaboration
This project is a collaboration between the University of Illinois at Urbana-Champaign, KTH Department of Sustainable Development and Stockholm University, Department of Physical Geography.

Watch the recorded presentation at the Digitalize in Stockholm 2023 event:

 

Follow us on social media to stay updated with our current research

Contacts

Picture of Zahra Kalantari

Zahra Kalantari

Associate Professor in Environmental and Engineering Geosciences at KTH, Co-PI of project Optimization of Agricultural Management for Soil Carbon Sequestration Using Deep Reinforcement Learning and Large-Scale Simulations at C3.ai DTI, Co-PI of project DeepAqua, Digital Futures Faculty

+46 8 790 86 93
zahrak@kth.se
Picture of Gia Destouni

Georgia Destouni

Professor of Hydrology and Water Resources, Department of Physical Geography at Stockholm University, Affiliated Professor of Engineering Hydrology, KTH Royal Institute of Technology, Researcher in project Optimization of Agricultural Management for Soil Carbon Sequestration Using Deep Reinforcement Learning and Large-Scale Simulations at Digital Futures, Digital Futures Faculty

+46 8-16 47 85
georgia.destouni@natgeo.su.se
Picture of Carla Ferreira

Carla Ferreira

Former Researcher, Stockholm University, Former Researcher in project Optimization of Agricultural Management for Soil Carbon Sequestration Using Deep Reinforcement Learning and Large-Scale Simulations at Digital Futures, Former Co-Pi of project DeepFlood: Enhancing large scale Flood Detection and Mapping using PolSAR, Metaheuristic, and Deep Learning Algorithms, Former Digital Futures Faculty

carla.ssf@gmail.com
Picture of Naira Hovakimyan

Naira Hovakimyan

W. Grafton and Lillian B. Wilkins Professor, University of Illinois at Urbana-Champaign

nhovakim@illinois.edu
Picture of Guillermo Marcillo

Guillermo Marcillo

Agronomy Data Scientist University of Illinois at Urbana-Champaign

Picture of Nicolas Martin

Nicolas Martin

Assistant Professor, Crop Sciences University of Illinois at Urbana-Champaign

nfmartin@illinois.edu
Picture of Pan Zhao

Pan Zhao

Postdoctoral Researcher, University of Illinois at Urbana-Champaign

panzhao2@illinois.edu