Presenters and attendants at the 2018 Poster Session

Monitoring and modeling water fluxes in Wisconsin Central Sands combining remote sensing data, machine learning, and Citizen Science data

Project Title Monitoring and modeling water fluxes in Wisconsin Central Sands combining remote sensing data, machine learning, and Citizen Science data
PI Name Jingyi Huang

jhuang426@wisc.edu

PI Affiliation UW-Madison, Department of Soil Science
Project Description Professor Huang’s lab (Soil Sensing & Monitoring Lab, https://soilsensingmonitoring.soils.wisc.edu/) has been developing high-resolution soil moisture and water flux (e.g., evapotranspiration) models in collaboration with colleagues by combining remote sensing imageries, maps of land surface parameters with machine learning algorithms. The models are being validated in Wisconsin and nationwide. Currently, Dr. Huang’ lab is collecting Citizen Science data and integrating them into the soil moisture and water flux models for mapping field-scale variations of soil moisture and evapotranspiration in Wisconsin Central Sands. The lab is looking for undergraduate researchers who are interested in soil moisture monitoring and modeling to collect Citizen Science data using handheld soil moisture probes across Wisconsin Central Sands regions during the summer of 2022 to improve the accuracies of the models for water resources management in Wisconsin. The undergraduate researchers will obtain hands-on experience on collecting soil moisture data in the field and have the opportunity to learn R programming for applying machine learning models for soil moisture and water fluxes mapping.
Qualifications Required Be able to drive a UW vehicle to collect field based soil moisture data; interested in water-related research; experiences in programming in R is desirable but not necessary; interested in learning R programming for machine learning modeling;
In-Person Tasks Using handheld soil moisture probes to collect ground-truth soil moisture data cross the Wisconsin Central Sands irrigation district; Using the collected soil moisture data (Citizen Science data) for calibrating soil moisture models pre-established using remote sensing data and machine learning models
Virtual / Remote Tasks Optional: learning machine learning modeling using R software. Reference course materials:

Soil Sci. 585 (Summer Semester, Online): https://soilsensingmonitoring.soils.wisc.edu/teaching/

Approx. Work Hours / Week 20
Keywords Soil moisture; Irrigation; Machine Learning; R Programming; Citizen Science;