Study on soil moisture content in soybean root zone based on UAV multispectral remote sensing
Abstract
Abstract: Timely acquisition of soil moisture in the root zone of farmland crops is the basis and key to achieve precise irrigation. In this study, based on UAV multi-spectral remote sensing technology, soybeans in Northwest China were selected as the research object, and ten vegetation indices with the best correlation with soybean soil moisture content were selected. Random Forest (RF), Extreme Learning Machine (ELM) and Back propagation neural network (BPNN) were used to construct the estimation model of soybean soil moisture content, and the model was verified. The results showed that the correlation between each spectral index and soil moisture content was high, and the correlation between spectral index OSAVI and soybean soil moisture content was the highest, which was 0.740. The change of OSAVI could monitor the change of soybean soil moisture content in real time. The accuracy of soybean LAI and aboveground biomass prediction model based on RF model was significantly higher than that of ELM and BP model. The R2, RMSE and MRE of soil moisture content monitoring model validation set were 0.803, 0.011 and 4.847, respectively. The results of this study can provide a theoretical basis for the application of UAV multi-spectral remote sensing in crop soil moisture monitoring, and provide a new way for rapid and accurate monitoring of farmland soil moisture and implementation of precision irrigation.
Keywords: soybean; soil moisture content; UAV remote sensing; vegetation index; machine learning
DOI: 10.33440/j.ijpaa.20230601.205
Citation: Tang Z J, Zhang W, Wang X, Xiang Y Z and Chen J Y. Study on soil moisture content in soybean root zone based on UAV multispectral remote sensing. Int J Precis Agric Aviat, 2023; 6(1): 9–15.
Full Text:
PDFReferences
Tian M L, Ge X Y, Ding J L, et al. (2020) Coupled Machine Learning and Unmanned Aerial Vehicle Based Hyperspectral Data for Soil moisture Content Estimation. Laser & Optoelectronics Progress, 57, 232–241. [In Chinese]
Rijal S, Zhang X D, Jia X H. (2013) Estimating Surface Soil Water Content in the Red River Valley of the North using Landsat 5 TM Data. Soil Science Society of America Journal, 77, 1133–1143. http://dx.doi.org/10.2136/sssaj2012.0295
Koreen M, Dan T, André P M, Murray R. (2018) Soil Moisture Monitoring in a Temperate Peatland Using Multi-Sensor Remote Sensing and Linear Mixed Effects. Remote Sensing, 10, 903–903. http://dx.doi.org/10.3390/ rs10060903
Esfahani L H, Torres-Rua A, Jensen A, McKee M. (2015) Assessment of Surface Soil Moisture Using High-Resolution Multi-Spectral Imagery and Artificial Neural Networks. Remote Sensing, 7, 2627–2646. http://dx.doi.org/10.3390/rs70302627
Yang X G, Yu Y. (2017) Remote sensing inversion of soil moisture based on laboratory reflectance spectral data. Transactions of the Chinese Society of Agricultural Engineering, 33, 195–199. [In Chinese]
Ma X C, Han F, Wu J G, et al. (2023) Optimizing crop water productivity and altering root distribution of Chardonnay grapevine (Vitis vinifera L.) in a silt loam soil through direct root-zone deficit irrigation. Agricultural Water Management, 277, 108072. http://dx.doi.org/10.1016/ J.AGWAT.2022.108072
Jiang X Q, Luo S J, Ye Q, et al. (2022) Hyperspectral Estimates of Soil Moisture Content Incorporating Harmonic Indicators and Machine Learning. Agriculture, 12, 1188–1188. http://dx.doi.org/10.3390/ AGRICULTURE12081188
Li X X, Zhu C G, Fu Z T, et al. (2020) Rapid Detection of Soil Moisture Content Based on UAV Multispectral Image. Spectroscopy and Spectral Analysis, 40, 1238–1242. [In Chinese]
MinGuk S, HyoSang S, Antonios T. (2021) Soil Moisture Retrieval Model Design with Multispectral and Infrared Images from Unmanned Aerial Vehicles Using Convolutional Neural Network. Agronomy, 11, 398–398. http://dx.doi.org/10.3390/AGRONOMY11020398
Bian J, Zhang Z T, Chen J Y, et al. (2019) Simplified Evaluation of Cotton Water Stress Using High Resolution Unmanned Aerial Vehicle Thermal Imagery. Remote Sensing, 11, 267. http://dx.doi.org/10.3390/ rs11030267
Chen J Y, Chen S B, Zhang Z T, et al. (2018) Investigation on Photosynthetic Parameters of Cotton during Budding Period by Multi-spectral Remote Sensing of Unmanned Aerial Vehicle. Transactions of the Chinese Society for Agricultural Machinery, 49, 230–239. [In Chinese]
Zhang Z T, Wang H F, Han W T, et al. (2018) Inversion of Soil Moisture Content Based on Multispectral Remote Sensing of UAVs. Transactions of the Chinese Society for Agricultural Machinery, 49, 173–181. [In Chinese]
Yang H B, Li F, Wang W, Yu K. (2021) Estimating Above-Ground Biomass of Potato Using Random Forest and Optimized Hyperspectral Indices. Remote Sensing, 13, 2339–2339. http://dx.doi.org/10.3390/ RS13122339
Yan X B, Qiao X X, Yang S, et al. (2023) Hyperspectral response and monitoring study of soil moisture content based on the optimized spectral index. Soil Science Society of America Journal, 87, 216–230. http://dx.doi.org/10.1002/SAJ2.20500
Romero M, Luo Y C, Su B F, et al. (2018) Vineyard water status estimation using multispectral imagery from an UAV platform and machine learning algorithms for irrigation scheduling management. Computers and Electronics in Agriculture, 147, 109–117. http://dx.doi.org/10.1016/ j.compag.2018.02.013
Liu T, Zhang H, Wang Z Y, He C, et al. (2021) Estimation of the leaf area index and chlorophyll content of wheat using UAV multi-spectrum images. Transactions of the Chinese Society of Agricultural Engineering, 37, 65–72. [In Chinese]
Yang N, Cui W X, Zhang Z T, et al. (2020) Soil salinity inversion at different depths using improved spectral index with UAV multispectral remote sensing. Transactions of the Chinese Society of Agricultural Engineering, 36, 13–21. [In Chinese]
Shi H Z, Guo J J, An J Q, et al. (2023) Estimation of Chlorophyll Content in Soybean Crop at Different Growth Stages Based on Optimal Spectral Index. Agronomy, 13, 663–663.
Ge X Y, Ding J L, Wang J Z, et al. (2018) Estimation of Soil Moisture Content Based on Competitive Adaptive Reweighted Sampling Algorithm Coupled with Machine Learning. Acta Optica Sinica, 38, 393–400. [In Chinese]
Chen W Q, Ding J L, Tian J, et al. (2017) Fitting of Hyperspectral Reflectance of Vegetation and Shallow Soil Water Content in Oasis of Arid Area. Transactions of the Chinese Society for Agricultural Machinery, 48, 229–236. [In Chinese]
Wang J Z, Ding J L, Ma X K, et al. (2018) Detection of Soil Moisture Content Based on UAV-derived Hyperspectral Imagery and Spectral Index in Oasis Cropland. Transactions of the Chinese Society for Agricultural Machinery, 49, 164–172. [In Chinese]
Wang W, Wang X P, Wang L J, et al. (2018) Soil moisture estimation for spring wheat in a semiarid area based on low-altitude remote-sensing data collected by small-sized unmanned aerial vehicles. Journal of Applied Remote Sensing, 12(2), 22207.
Sha S, Hu D, Wang L J, et al. (2023) Study on Remote Sensing Monitoring Method of Soil Moisture in Henan Province. Meteorological and Environmental Sciences, 46, 91–99. [In Chinese]
Seo M, Shin H, Tsourdos A. (2021). Soil Moisture Retrieval Model Design with Multispectral and Infrared Images from Unmanned Aerial Vehicles Using Convolutional Neural Network. Agronomy, 11(2), 398.
Deng J T, Pan S J, Zhou M G, et al. (2023) Optimum sampling window size and vegetation index selection for low-altitude multispectral estimation of root soil moisture content for Xuxiang Kiwifruit. Agricultural Water Management, 282, 108297. http://dx.doi.org/10.1016/J.AGWAT.2023.108297
Cheng E H, Zhang B, Peng D L, et al. (2022) Wheat yield estimation using remote sensing data based on machine learning approaches. Frontiers in Plant Science, 1090970. http://dx.doi.org/10.3389/FPLS.2022.1090970
Liakos K G, Busato P, Moshou D, et al. (2018) Machine Learning in Agriculture: A Review. Sensors, 18, 2674–2674. http://dx.doi.org/ 10.3390/s18082674
Szabó B, Szatmári G, Takács K, et al. (2019) Mapping soil hydraulic properties using random-forest-based pedotransfer functions and geostatistics. Hydrology and Earth System Sciences, 23, 2615–2635.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.