Visual Monitoring Platform of Soil Organic Carbon Based on Unmanned Aerial Vehicle Multispectral Remote Sensing

doi:10.11924/j.issn.1000-6850.casb2025-0552

Abstract

Abstract:

Obtaining information on the content and distribution of soil organic carbon (SOC) is of great significance for the development of agricultural production. In this study, we designed and developed a SOC visual monitoring platform by innovatively integrating unmanned aerial vehicle (UAV) multispectral remote sensing images, Web development technology, machine learning algorithms and database technology. The system was applied to monitor the reclaimed farmlands in mining area of Yanzhou District, Jining City, Shandong Province. The results show that: (1) SOC content can be predicted quickly and accurately using UAV multispectral remote sensing images and machine learning algorithms. The light gradient boosting machine (LightGBM) model is the best prediction model, with the coefficient of determination (R²) of the modeling set and the validation set being 0.825 and 0.793, respectively; and (2) the system realizes visualizations for SOC data statistics, content grading, geographic distribution, and more. Therefore, the results of the study can provide scientific reference for the nutrient management of farmland at the field scale.

Key words: soil organic carbon, unmanned aerial vehicle, multispectral, Web development, machine learning, monitoring platform

CLC Number:

S126电子技术、计算机技术在农业上的应用

WANG Zhikun, LI Xinju, HU Xiao. Visual Monitoring Platform of Soil Organic Carbon Based on Unmanned Aerial Vehicle Multispectral Remote Sensing[J]. Chinese Agricultural Science Bulletin, 2026, 42(11): 195-201.

Figures/Tables 9

References 22

[1]	黄昌勇. 土壤学[M]. 北京: 中国农业出版社, 2000:33,44-46.
[2]	GERKE J. The central role of soil organic matter in soil fertility and carbon storage[J]. Soil systems, 2022, 6(2):33. doi: 10.3390/soilsystems6020033 URL
[3]	刘焕军, 张美薇, 杨昊轩, 等. 多光谱遥感结合随机森林算法反演耕作土壤有机质含量[J]. 农业工程学报, 2020, 36(10):134-140.
[4]	ANGELOPOULOU T, CHABRILLAT S, PIGNATTI S, et al. Evaluation of airborne hyspex and spaceborne PRISMA hyperspectral remote sensing data for soil organic matter and carbonates estimation[J]. Remote sensing, 2023, 15(4):1106. doi: 10.3390/rs15041106 URL
[5]	DUAN X L, MAQSOOM A, KHALIL U, et al. Enhancing soil moisture retrieval in semi-arid regions using machine learning algorithms and remote sensing data[J]. Applied soil ecology, 2024, 204:105687. doi: 10.1016/j.apsoil.2024.105687 URL
[6]	王东旭, 王杰, 诸云强, 等. 云南省土壤墒情监测系统的设计与实现[J]. 灌溉排水学报, 2016, 35(10):83-89.
[7]	ZHANG T, ZHANG Y, WANG A, et al. Intelligent analysis cloud platform for soil moisture-nutrients-salinity content based on quantitative remote sensing[J]. Atmosphere, 2022, 14(1):23. doi: 10.3390/atmos14010023 URL
[8]	SONG Y Q, PAN Y X, XIANG M Y, et al. A WebGIS-based system for supporting saline-alkali soil ecological monitoring: a case study in Yellow River Delta, China[J]. Remote sensing, 2024, 16(11):1948. doi: 10.3390/rs16111948 URL
[9]	孙刚, 黄文江, 陈鹏飞, 等. 轻小型无人机多光谱遥感技术应用进展[J]. 农业机械学报, 2018, 49(3):1-17.
[10]	ZHANG Z X, NIU B B, LI X J, et al. Inversion of soil salinity in China’s Yellow River Delta using unmanned aerial vehicle multispectral technique[J]. Environmental monitoring and assessment, 2023, 195:245. doi: 10.1007/s10661-022-10831-0
[11]	张智韬, 魏广飞, 姚志华, 等. 基于无人机多光谱遥感的土壤含盐量反演模型研究[J]. 农业机械学报, 2019, 50(12):151-160.
[12]	HEIL J, JÖRGES C, STUMPE B. Fine-scale mapping of soil organic matter in agricultural soils using UAVs and machine learning[J]. Remote sensing, 2022, 14(14):3349. doi: 10.3390/rs14143349 URL
[13]	WANG Y F, MA Y, ZHOU F R, et al. More precise monitoring of soil moisture content in agricultural fields by upscaling conversion of multispectral image data from unmanned aerial vehicles[J]. IEEE access, 2024, 12:79892-79904. doi: 10.1109/ACCESS.2024.3407107 URL
[14]	郝金雨. 基于无人机多光谱影像的土壤含水率检测研究[D]. 泰安: 山东农业大学, 2023.
[15]	杨玮, 于滈, 李浩, 等. 基于多光谱图像的土壤有机质含量检测系统与APP研究[J]. 农业机械学报, 2023, 54(9):270-278.
[16]	胡晓, 臧玉龙, 高睿康, 等. 基于无人机多光谱遥感和机器学习的烟田土壤碱解氮估测[J]. 中国烟草科学, 2024, 45(5):95-103.
[17]	DIAZ-GONZALEZ F A, VUELVAS J, CORREA C A, et al. Machine learning and remote sensing techniques applied to estimate soil indicators-review[J]. Ecological indicators, 2022, 135:108517. doi: 10.1016/j.ecolind.2021.108517 URL
[18]	AZZEH M, NEAGU D, COWLING P I. Fuzzy grey relational analysis for software effort estimation[J]. Empirical software engineering, 2010, 15(1):60-90. doi: 10.1007/s10664-009-9113-0 URL
[19]	DELGADO J, FERRADA H, NAVARRO C A. A succinct and approximate greedy algorithm for the minimum set cover problem[J]. Journal of computational science, 2024, 81:102378. doi: 10.1016/j.jocs.2024.102378 URL
[20]	许睿娉, 李俊颖, 张冰姿, 等. 高潜水位煤矿区不同充填材料复垦土壤有机碳垂直分布特征与敏感性分析[J]. 煤炭学报, 2025, 50(9):4487-4501.
[21]	鲍士旦. 土壤农化分析(第三版)[M]. 北京: 中国农业出版社, 2000:30-34.
[22]	全国土壤普查办公室. 中国土壤普查技术[M]. 北京: 中国农业出版社, 1992:87.

SOC/(g/kg)	NDVI	EVI	CI_red-edge	...
9.0	-0.336	0.339	1.014	...
9.5	-0.341	0.318	1.035	...
11.0	-0.440	0.365	1.568	...
...	...	...	...	...

SOC/(g/kg)	NDVI	EVI	CI_red-edge	...
9.0	-0.336	0.339	1.014	...
9.5	-0.341	0.318	1.035	...
11.0	-0.440	0.365	1.568	...
...	...	...	...	...

光谱变量	计算公式
NDVI	(Nir-R)/(Nir+R)
NDSI	(R-Nir)/(R+Nir)
SAVI	1.5×(Nir-R)/(Nir+R+0.5)
CI_red-edge	Nir/Reg-1
EVI	2.5×(Nir-R)/(Nir+6×R-7.5×B+1)
TVI	0.5×[120×(Nir-G)]-200×(R-G)
NDVI+Reg	(Nir-R)/(Nir+R)+Reg
NDSI+Reg	(R-Nir)/(R+Nir)+Reg
SAVI+Reg	1.5×(Nir-R)/(Nir+R+0.5)+Reg
CIred-edge+R	Nir/Reg-1+R
EVI+Reg	2.5×(Nir-R)/(Nir+6×R-7.5×B+1)+Reg
TVI+Reg	0.5×[120×(Nir-G)]-200×(R-G))+Reg
lgR	lgR
lgR+Reg	lgR+Reg
lgReg	lgReg
R/Reg	R/Reg
R/(Reg+Nir)	R/(Reg+Nir)
1/Nir	1/Nir

光谱变量	计算公式
NDVI	(Nir-R)/(Nir+R)
NDSI	(R-Nir)/(R+Nir)
SAVI	1.5×(Nir-R)/(Nir+R+0.5)
CI_red-edge	Nir/Reg-1
EVI	2.5×(Nir-R)/(Nir+6×R-7.5×B+1)
TVI	0.5×[120×(Nir-G)]-200×(R-G)
NDVI+Reg	(Nir-R)/(Nir+R)+Reg
NDSI+Reg	(R-Nir)/(R+Nir)+Reg
SAVI+Reg	1.5×(Nir-R)/(Nir+R+0.5)+Reg
CIred-edge+R	Nir/Reg-1+R
EVI+Reg	2.5×(Nir-R)/(Nir+6×R-7.5×B+1)+Reg
TVI+Reg	0.5×[120×(Nir-G)]-200×(R-G))+Reg
lgR	lgR
lgR+Reg	lgR+Reg
lgReg	lgReg
R/Reg	R/Reg
R/(Reg+Nir)	R/(Reg+Nir)
1/Nir	1/Nir

波段名称	中心波长/nm	带宽/nm	校正系数
蓝光波段	450	30	0.61
绿光波段	555	27	0.60
红光波段	660	22	0.61
红边波段	720	10	0.62
近红外波段	840	30	0.60