UAV multispectral remote sensing for the estimation of SPAD values at various growth stages of maize under different irrigation levels

Authors: MA, WEITONG - Northwest A&f University; WENTING, HAN - Northwest A&f University; Zhang, Huihui; CUI, XIN - Northwest A&f University; ZHANG, LIYUAN - Jiangsu University; SHAO, GUOMIN - Northwest A&f University; NIU, YAXIAO - Jiangsu University; HUANG, SHENJIN - Harbin Institute Of Technology (HIT)

Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/15/2024
Publication Date: 10/21/2024
Citation: Ma, W., Wenting, H., Zhang, H., Cui, X., Zhang, L., Shao, G., Niu, Y., Huang, S. 2024. UAV multispectral remote sensing for the estimation of SPAD values at various growth stages of maize under different irrigation levels. Computers and Electronics in Agriculture. Vol 227, Part 1, December 2024, 109566. https://doi.org/10.1016/j.compag.2024.109566.
DOI: https://doi.org/10.1016/j.compag.2024.109566

Interpretive Summary: Plants need chlorophyll to do photosynthesis. A portable device, called a SPAD meter, can measure how much chlorophyll is in a plant's leaves. This is helpful for farmers to know how their crops are growing and how much grain they can expect to get. Drone remote sensing can also be used to measure chlorophyll levels over a big area. But the current models used to predict chlorophyll levels by drone images have some limitations. They usually only work for a whole crop growing season, don’t consider crop water status or other factors, and don’t include plant-related information as inputs. This makes it hard to accurately estimate chlorophyll levels at different times during the growing season. In this study, we used drone images to predict chlorophyll content in maize plants under different irrigation at different growth stages. We tested three computer models and one performed better than the others for all growth stages in two years. We also found that including separately measured leaf area index and plant height in the model led to improved predictions. Farmers and land managers could benefit significantly from this study, as it offers a drone-based solution that can assist them in effectively caring for their crops, even when the plants are experiencing water stress.

Technical Abstract: Chlorophyll is crucial for photosynthesis in plants and the readings by a SPAD meter (Soil and Plant Analyzer Development) can be used to represent leaf chlorophyll content for monitoring crop growth status and predicting grain yield. Remote sensing technology has shown potential in non-destructive monitoring of SPAD values over large areas, but current SPAD inversion models are limited in their ability to incorporate multiple principal components besides spectral parameters, adapt to other variables such as water stress, and predict SPAD only throughout the entire growth period. This two-year study used crop parameters (PH and LAI) and vegetative indices (VI) derived from unmanned aerial vehicle (UAV) multispectral images to develop SPAD prediction models for maize under different irrigation levels in the 2018 and 2019 growing seasons in Inner Mongolia, China. Two nonlinear machine learning models, random forest (RF) and support vector regression (SVR), and a multiple statistical regression method (partial least squares regression (PLSR)) were used. The results showed that the VIs with a high correlation with SPAD varied at each growth stage. PLSR performed better than RF and SVR for the whole growth period, especially at the reproductive stage (R). LAI and PH did not always improve prediction accuracy, but adding crop parameters did increase the correlation coefficient between predicted values and biomass by 8.3%. This study provides valuable insights into the estimation of SPAD at different growth stages of maize under varying water stress levels using UAV data and crop parameters, offering guidance for farmland management and yield prediction.