Nitrogen Estimation for Wheat Using UAV-Based and Satellite Multispectral Imagery, Topographic Metrics, Leaf Area Index, Plant Height, Soil Moisture, and Machine Learning Methods

Jody Yu,Yang Song,Brigitte Leblon,Jinfei Wang

doi:10.3390/nitrogen3010001

Abstract

To improve productivity, reduce production costs, and minimize the environmental impacts of agriculture, the advancement of nitrogen (N) fertilizer management methods is needed. The objective of this study is to compare the use of Unmanned Aerial Vehicle (UAV) multispectral imagery and PlanetScope satellite imagery, together with plant height, leaf area index (LAI), soil moisture, and field topographic metrics to predict the canopy nitrogen weight (g/m2) of wheat fields in southwestern Ontario, Canada. Random Forests (RF) and support vector regression (SVR) models, applied to either UAV imagery or satellite imagery, were evaluated for canopy nitrogen weight prediction. The top-performing UAV imagery-based validation model used SVR with seven selected variables (plant height, LAI, four VIs, and the NIR band) with an R2 of 0.80 and an RMSE of 2.62 g/m2. The best satellite imagery-based validation model was RF, which used 17 variables including plant height, LAI, the four PlanetScope bands, and 11 VIs, resulting in an R2 of 0.92 and an RMSE of 1.75 g/m2. The model information can be used to improve field nitrogen predictions for the effective management of N fertilizer.

Highlights

Precision agriculture (PA) is a management technique that selectively applies crop farming resources such as fertilizer, water, pesticides, and herbicides based on the plant needs within a field [1,2,3]
This study aims to evaluate machine learning modelling methods with plant spectral, biophysical, and field environmental variables to predict canopy nitrogen weight (CNW) in wheat crops using Unmanned Aerial Vehicle (UAV) and satellite-based imagery
The canopy N weight for the wheat fields increased in variation during the fieldwork season (Figure 4)

Summary

Introduction

Precision agriculture (PA) is a management technique that selectively applies crop farming resources such as fertilizer, water, pesticides, and herbicides based on the plant needs within a field [1,2,3]. Nitrogen is an essential macronutrient to plants as a major constituent of organic material including enzymic processes, chlorophyll, and oxidationreduction reactions; levels of nitrogen in plant tissue can indicate yield potential and crop health [4]. Nutrients that have been added beyond the critical level of maximum growth can continue to accumulate in the plant tissue without any further yield increase [4]. In grain crops such as wheat, excessive nitrogen can cause plant stems to grow tall to the point of lodging—the stems bend over, making it difficult to harvest and increasing the chances of grain moisture and disease, and often reducing yield significantly [8]. The availability of water to a plant depends on the weather conditions during the growing season, the soil moisture, and the field micro-topography affecting water flow and accumulation [10,11]. Understanding a field’s characteristics as well as monitoring plant biophysical characteristics including height, leaf area, and leaf colour can provide useful information in nitrogen fertilizer applications

Objectives

Methods

Results

Discussion

Conclusion