Remote Sensing Precipitation for Agricultural Applications using Machine-Learning Methods
Abstract
Precipitation is one most important meteorological variables for agriculture. Too much or too little rainfall can be harmful to crops. Drought can kill crops from insufficient water, while soil nutrients may diminish and erosion increase during the wet season. Extreme rainfall causes flash floods what could inundate agricultural land. Effective rainfall measurement and forecasting over the crop growing seasons are critical for agricultural productivity. Remote sensing techniques provide a unique way to monitoring precipitation over ungauged basins and developing counties where gauges are limited. Recent development in computational Intelligence has shown good progress in using a large amount of in-situ and remote sensing data to improve the quality of precipitation measurement. In this presentation, integration of multi-satellite sensors for precipitation estimation using deep neural networks (DNNs) will be introduced. Case studies will cover (1) monitoring of precipitation of extreme storm events for flood forecasting and (2) application of remote sensing information in land hydrologic model (ParFlow) simulation to estimate surface wetness and soil moisture contents over the agriculture lands under various irrigation scenarios.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2019
- Bibcode:
- 2019AGUFM.H33A..03H
- Keywords:
-
- 1805 Computational hydrology;
- HYDROLOGY;
- 1875 Vadose zone;
- HYDROLOGY;
- 1879 Watershed;
- HYDROLOGY;
- 1942 Machine learning;
- INFORMATICS