Using Linear Regression, Random Forests, and Support Vector Machine with Unmanned Aerial Vehicle Multispectral Images to Predict Canopy Nitrogen Weight in Corn

• Published in: Remote sensing (Basel, Switzerland) Vol. 12; no. 13; p. 2071
• Main Authors: Lee, Hwang, Wang, Jinfei, Leblon, Brigitte
• Format: Journal Article
• Language: English
• Published: MDPI AG 01.07.2020
• Subjects: canopy; canopy nitrogen weight; corn; crops; economic impact; farmers; fertilizer application; image analysis; machine learning; multispectral imagery; nitrogen; nitrogen fertilizers; nitrogen management; Ontario; plant growth; precision agriculture; processing time; Random Forests; regression analysis; remote sensing; support vector machines; Unmanned Aerial Vehicle (UAV); unmanned aerial vehicles; vegetation index; water supply; Ontario
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs12132071

The optimization of crop nitrogen fertilization to accurately predict and match the nitrogen (N) supply to the crop N demand is the subject of intense research due to the environmental and economic impact of N fertilization. Excess N could seep into the water supplies around the field and cause unnecessary spending by the farmer. The drawbacks of N deficiency on crops include poor plant growth, ultimately reducing the final yield potential. The objective of this study is to use Unmanned Aerial Vehicle (UAV) multispectral imagery to predict canopy nitrogen weight (g/m2) of corn fields in south-west Ontario, Canada. Simple/multiple linear regression, Random Forests, and support vector regression (SVR) were established to predict the canopy nitrogen weight from individual multispectral bands and associated vegetation indices (VI). Random Forests using the current techniques/methodologies performed the best out of all the models tested on the validation set with an R2 of 0.85 and Root Mean Square Error (RMSE) of 4.52 g/m2. Adding more spectral variables into the model provided a marginal improvement in the accuracy, while extending the overall processing time. Random Forests provided marginally better results than SVR, but the concepts and analysis are much easier to interpret on Random Forests. Both machine learning models provided a much better accuracy than linear regression. The best model was then applied to the UAV images acquired at different dates for producing maps that show the spatial variation of canopy nitrogen weight within each field at that date.