Modeling maize above-ground biomass based on machine learning approaches using UAV remote-sensing data

Моделирование надземной биомассы кукурузы на основе методов машинного обучения с использованием данных дистанционного зондирования с БПЛА
Bo Xu, Zhenhai Li, Guijun Yang, Xiaodong Yang, Liang Han, Haikuan Feng, Hao Frank Yang, Huayang Dai
2019-02-04

BIOVP volumetric indicatorUAV remote sensingmachine learning regressionmaize above-ground biomassrecursive feature elimination
BACKGROUND: Above-ground biomass (AGB) is a basic agronomic parameter for field investigation and is frequently used to indicate crop growth status, the effects of agricultural management practices, and the ability to sequester carbon above and below ground. The conventional way to obtain AGB is to use destructive sampling methods that require manual harvesting of crops, weighing, and recording, which makes large-area, long-term measurements challenging and time consuming. However, with the diversity of platforms and sensors and the improvements in spatial and spectral resolution, remote sensing is now regarded as the best technical means for monitoring and estimating AGB over large areas. RESULTS: In this study, we used structural and spectral information provided by remote sensing from an unmanned aerial vehicle (UAV) in combination with machine learning to estimate maize biomass. Of the 14 predictor variables, six were selected to create a model by using a recursive feature elimination algorithm. Four machine-learning regression algorithms (multiple linear regression, support vector machine, artificial neural network, and random forest) were evaluated and compared to create a suitable model, following which we tested whether the two sampling methods influence the training model. To estimate the AGB of maize, we propose an improved method for extracting plant height from UAV images and a volumetric indicator (i.e., BIOVP). The results show that (1) the random forest model gave the most balanced results, with low error and a high ratio of the explained variance for both the training set and the test set. (2) BIOVP can retain the largest strength effect on the AGB estimate in four different machine learning models by using importance analysis of predictors. (3) Comparing the plant heights calculated by the three methods with manual ground-based measurements shows that the proposed method increased the ratio of the explained variance and reduced errors. CONCLUSIONS: These results lead us to conclude that the combination of machine learning with UAV remote sensing is a promising alternative for estimating AGB. This work suggests that structural and spectral information can be considered simultaneously rather than separately when estimating biophysical crop parameters.
1
Among multiple linear regression, support vector machine, artificial neural network, and random forest, random forest achieved the most balanced performance, with low errors and high explained variance in training and testing.
2
An improved UAV-based plant-height extraction method increased explained variance and reduced errors compared with three alternative height-calculation methods and manual ground measurements.
3
Recursive feature elimination reduced 14 predictor variables to six for biomass model construction.
4
The proposed volumetric indicator BIOVP retained the strongest influence on above-ground biomass estimates across all four machine-learning models.
5
UAV structural and spectral data combined with machine learning were used to estimate maize above-ground biomass non-destructively.

Maize above-ground biomass (AGB) estimated from UAV remote-sensing data

the relationships between UAV-derived structural and spectral predictors, including plant height and BIOVP, and maize above-ground biomass, including the comparative performance of machine-learning regression models

Publication Details
Publication Date
2019-02-04
Journal
Publisher
ISSN
Cited by
432
Access Type
Author Information
Authors
Bo Xu
Zhenhai Li
Guijun Yang
Xiaodong Yang
Liang Han
Haikuan Feng
Hao Frank Yang
Huayang Dai
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%