An Efficient NDVI-Based NARX ML Model for Predicting Soil Moisture in Basella alba for Precision Irrigation

Overview

Leafy vegetables like Malabar spinach require optimal soil moisture (SM) to ensure steady physiological activity, improved nutrient uptake, and higher leaf yield. Too much or too little water application, based on current ET based irrigation method may affect plant growth, vigor, and vegetable quality. Too much watering is not only a waste but also can drain nutrient out from root zone. Since health of leafy vegetable, like Malabar spinach are strongly associated with canopy greenness, Normalized Difference Vegetation Index (NDVI) which quantifies vegetation greenness can serve as a reliable indicator of this crop health. NDVI variations reflecting change in SM, can provide an opportunity to develop machine learning (ML) models for efficient irrigation. The nonlinear autoregressive exogenous (NARX) algorithm, which can use external variables and past system response to predict future system response is used in this research. With a goal to predict required SM to produce healthier Malabar spinach, NARX ML methodology consist of data collection, data processing including geo-processing, NDVI calculations and data processing for ML model, NARX development, model parameter selection, and analyzing model outputs has been presented here to capture SM dynamics using past SM and NDVI data to predict required SM. Results show that NARX model can successfully capture SM dynamics to predict peak and valley of daily SM level efficiently with high accuracy with R value for model prediction as high as 0.91. An analysis shows that application of this model can save significant revenue if the model is installed in a pump controller

Competition history

• CSEF 2026 Environmental Engineering (Track 2) (Senior Division) · Entry S-12-17

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

• All Environmental Engineering projects
• CSEF Environmental Engineering projects
• Every CSEF 2026 project