Dear All,
Leveraging the recent AI boom to substantially improve agroecosystem prediction is a paradigm-shift topic in the coming decade. In particular, Knowledge Guided Machine Learning (KGML) as a hybrid modeling approach has demonstrated great potential in several geoscience disciplines. We would invite highly motivated applicants to further develop and apply KGML to investigate a range of critical questions concerning agroecosystem sustainability.
Successful candidates will be supported to work on one or more topics listed below:
● Develop AI-driven methods to assimilate remote sensing and low-cost sensor observations into KGML models to improve the prediction of GHG emissions, climate risks, and crop productions.
● The application of KGML for Climate-Smart Agriculture and optimizing management practices.
● Modeling the impacts of agricultural nitrogen (N) management on air and water quality.
● Modeling agricultural phosphorous (P) cycle, with a focus on P losses from cropland to water bodies and coupling with N cycle.
● GeoAI for commodity mapping and sustainable supply chain management
The successful applicants will be supervised by Dr. Zhenong Jin (https://bbe.umn.edu/people/zhenong-jin) and collaborate closely with leading experts from UIUC, Stanford, Lawrence Berkeley National Laboratory, and many more academia and industrial collaborators.
Essential Qualifications:
All applicants are
expected to have a strong quantitative background. The successful candidate
will need to meet at least two of the following expectations:
Applications: Qualified candidates must send a short introduction email and CV to Dr. Zhenong Jin ([log in to unmask]). The interview will start immediately until all positions are filled. A competitive salary will be provided based on experience. The positions have a funding commitment for two years, with possibilities for renewal or promotion upon performance.
Best,
Jin