fao56

Comparing LightGBM, a vanilla neural net, and a Physics-Informed NN for ETo estimation. The PINN embeds FAO-56 physics in its loss; reproducible synthetic data show physics helps most when measurements are scarce or noisy. Ready-to-run code.

Sensor-free mango orchard digital twin using weather, soil, Sentinel-2, FAO-56 water balance, and forecast-aware irrigation advisory.

This repository is to serve as the submittal of my semester project for the class "Soil Physics Theory" at Oklahoma State University. Over the course of this project I want to take in field soil moisture data and use it to train a FAO 56 based model to effectively predict soil moisture in crop fields.

A modular Python pipeline with a Tkinter desktop GUI for reference/crop evapotranspiration, soil-water balance, irrigation scheduling, and full farm-report generation for five crops grown around Zaria, Nigeria.