D-PAL Lab Logo
Banner 1
Banner 2
Banner 3
Banner 4
Banner 5
Banner 6
Banner 7
Banner 8
Banner 9
Banner 10
Digital and Precision Agriculture Lab, University of MarylandPrecision Agriculture Technology Conference on Feb 26, 2026 at the Crowne Plaza, Annapolis.Digital and Precision Agriculture Lab, University of MarylandPrecision Agriculture Technology Conference on Feb 26, 2026 at the Crowne Plaza, Annapolis.
Back to Research Projects
AI-Enabled Precision Irrigation Decision Support Tool
AI & ML

Intelligent Irrigation Decision Platform

AI-based irrigation decision tool to help farmers apply optimal water amounts, reducing water and nutrient use while improving productivity.

Our lab is developing an AI-based irrigation decision tool designed to help farmers apply the optimal amount of water to their fields. This approach reduces water and nutrient usage, ultimately improving agricultural productivity while minimizing environmental contamination caused by runoff and nutrient leaching.

Sub-projects

Artificial Intelligence (AI)-Enabled Precision Irrigation Decision Support Tool

Artificial Intelligence (AI)-Enabled Precision Irrigation Decision Support Tool

Dr. Fitsum Teshome

Development and testing of the AI-enabled precision irrigation decision support tool with partner growers.

Images

Artificial Intelligence (AI)-Enabled Precision Irrigation Decision Support Tool 1
Artificial Intelligence (AI)-Enabled Precision Irrigation Decision Support Tool 2
Artificial Intelligence (AI)-Enabled Precision Irrigation Decision Support Tool 3
Artificial Intelligence (AI)-Enabled Precision Irrigation Decision Support Tool 4
Evaluating the effect of data aggregation in different Artificial Intelligence (AI) models for irrigation scheduling

Evaluating the effect of data aggregation in different Artificial Intelligence (AI) models for irrigation scheduling

Ajay Sengar

Evaluating the effect of data aggregation in different AI models for irrigation scheduling.

Irrigation predictions using integration of soil physics into Artificial Intelligence (AI) models

Irrigation predictions using integration of soil physics into Artificial Intelligence (AI) models

Nayana Gadde

Irrigation predictions using integration of soil physics into AI models.

Outcomes

  • Reduced irrigation water use in pilot fields compared to conventional scheduling.
  • Lower nutrient leaching risk through improved timing of applications.
  • User-friendly decision support interface for Maryland growers.