Predicting Particle Size and Soil Organic Carbon of Soil Profiles Using VIS-NIR-SWIR Hyperspectral Imaging and Machine Learning Models

被引:4
|
作者
de Oliveira, Karym Mayara [1 ]
Goncalves, Joao Vitor Ferreira [1 ]
Furlanetto, Renato Herrig [2 ]
de Oliveira, Caio Almeida [1 ]
Mendonca, Weslei Augusto [1 ]
Haubert, Daiane de Fatima da Silva [1 ]
Crusiol, Luis Guilherme Teixeira [3 ]
Falcioni, Renan [1 ]
de Oliveira, Roney Berti [1 ]
Reis, Amanda Silveira [1 ]
Ecker, Arney Eduardo do Amaral [4 ]
Nanni, Marcos Rafael [1 ]
机构
[1] Univ Estadual Maringa, Dept Agron, Ave Colombo 5790, BR-87020900 Maringa, PR, Brazil
[2] Univ Florida, Gulf Coast Res & Educ Ctr, Wimauma, FL 33598 USA
[3] Embrapa Soja Empresa Brasileira Pesquisa Agr, BR-86044764 Londrina, Parana, Brazil
[4] Ctr Univ Inga UNINGA, Dept Agron, Rod PR 317,6114, BR-87035510 Maringa, Parana, Brazil
关键词
data modeling; predictive model; remote sensing; spectroscopy of soils; spectral signature; REFLECTANCE SPECTROSCOPY; NITROGEN; TEXTURE;
D O I
10.3390/rs16162869
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Modeling spectral reflectance data using machine learning algorithms presents a promising approach for estimating soil attributes. Nevertheless, a comprehensive investigation of the most effective models, parameters, wavelengths, and data acquisition techniques is essential to ensure optimal predictive accuracy. This work aimed to (a) explore the potential of the soil spectral signature obtained in different spectral bands (VIS-NIR, SWIR, and VIS-NIR-SWIR) and, by using hyperspectral imaging and non-imaging sensors, in the predictive modeling of soil attributes; and (b) analyze the accuracy of different ML models in predicting particle size and soil organic carbon (SOC) applied to the spectral signature of different spectral bands. Six soil monoliths, located in the central north region of Parana, Brazil, were collected and scanned via hyperspectral cameras (VIS-NIR camera and SWIR camera) and spectroradiometer (VIS-NIR-SWIR) in the laboratory. The spectral signature of the soils was analyzed and subsequently applied to ML models to predict particle size and SOC. Each set of data obtained by the different sensors was evaluated separately. The algorithms used were k-nearest neighbors (KNN), support vector machine (SVM), random forest (RF), linear regression (LR), artificial neural network (NN), and partial least square regression (PLSR). The most promising predictive performance was observed for the complete VIS-NIR-SWIR spectrum, followed by SWIR and VIS-NIR. Meanwhile, KNN, RF, and NN models were the most promising algorithms in estimating soil attributes for the dataset obtained from both sensors. The general mean R2 (determination coefficient) values obtained using these models, considering the different spectral bands evaluated, were around 0.99, 0.98, and 0.97 for sand prediction, and around 0.99, 0.98, and 0.96 for clay prediction. The lower performances, obtained for the datasets from both sensors, were observed for silt and SOC, with R2 results between 0.40 and 0.59 for these models. KNN demonstrated the best predictive performance. Integrating effective ML models with robust sample databases, obtained by advanced hyperspectral imaging and spectroradiometers, can enhance the accuracy and efficiency of soil attribute prediction.
引用
收藏
页数:21
相关论文
共 42 条
  • [1] Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning Models
    de Oliveira, Karym Mayara
    Falcioni, Renan
    Goncalves, Joao Vitor Ferreira
    de Oliveira, Caio Almeida
    Mendonca, Weslei Augusto
    Crusiol, Luis Guilherme Teixeira
    de Oliveira, Roney Berti
    Furlanetto, Renato Herrig
    Reis, Amanda Silveira
    Nanni, Marcos Rafael
    REMOTE SENSING, 2023, 15 (19)
  • [2] Performance of global and regional VIS-NIR-SWIR models in predicting soil copper and zinc in vineyards in southern Brazil
    Sangoi, Daniely Vaz da Silva
    Dalmolin, Ricardo Simao Diniz
    Moura-Bueno, Jean Michel
    Pedron, Fabricio de Araujo
    Tiecher, Tales
    Brunetto, Gustavo
    ENVIRONMENTAL MONITORING AND ASSESSMENT, 2025, 197 (03)
  • [3] Combining Vis-NIR-SWIR Spectroscopy and Machine Learning to Predict Soil Available Copper and Zinc in Southern Brazil Vineyards
    Sangoi, Daniely Vaz da Silva
    Dalmolin, Ricardo Simao Diniz
    Moura-Bueno, Jean Michel
    Pedron, Fabricio de Araujo
    Brunetto, Gustavo
    Hindersmann, Jacson
    Grando, Douglas Luiz
    Fontana, Agnes Estela
    JOURNAL OF SOIL SCIENCE AND PLANT NUTRITION, 2025,
  • [4] Machine-learning-based quantitative estimation of soil organic carbon content by VIS/NIR spectroscopy
    Ding, Jianli
    Yang, Aixia
    Wang, Jingzhe
    Sagan, Vasit
    Yu, Danlin
    PEERJ, 2018, 6
  • [5] Evaluation of Machine Learning Approaches to Predict Soil Organic Matter and pH Using vis-NIR Spectra
    Yang, Meihua
    Xu, Dongyun
    Chen, Songchao
    Li, Hongyi
    Shi, Zhou
    SENSORS, 2019, 19 (02):
  • [6] Estimating Soil Organic Carbon Using VIS/NIR Spectroscopy with SVMR and SPA Methods
    Peng, Xiaoting
    Shi, Tiezhu
    Song, Aihong
    Chen, Yiyun
    Gao, Wenxiu
    REMOTE SENSING, 2014, 6 (04) : 2699 - 2717
  • [7] Mapping Particle Size and Soil Organic Matter in Tropical Soil Based on Hyperspectral Imaging and Non-Imaging Sensors
    Nanni, Marcos Rafael
    Dematte, Jose Alexandre Melo
    Rodrigues, Marlon
    dos Santos, Glaucio Leboso Alemparte Abrantes
    Reis, Amanda Silveira
    de Oliveira, Karym Mayara
    Cezar, Everson
    Furlanetto, Renato Herrig
    Crusiol, Luis Guilherme Teixeira
    Sun, Liang
    REMOTE SENSING, 2021, 13 (09)
  • [8] Development of a Soil Organic Matter Content Prediction Model Based on Supervised Learning Using Vis-NIR/SWIR Spectroscopy
    Kim, Min-Jee
    Lee, Hye-In
    Choi, Jae-Hyun
    Lim, Kyoung Jae
    Mo, Changyeun
    SENSORS, 2022, 22 (14)
  • [9] Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy
    Morellos, Antonios
    Pantazi, Xanthoula-Eirini
    Moshou, Dimitrios
    Alexandridis, Thomas
    Whetton, Rebecca
    Tziotzios, Georgios
    Wiebensohn, Jens
    Bill, Ralf
    Mouazen, Abdul M.
    BIOSYSTEMS ENGINEERING, 2016, 152 : 104 - 116
  • [10] A memory-based learning approach utilizing combined spectral sources and geographical proximity for improved VIS-NIR-SWIR soil properties estimation
    Tziolas, Nikolaos
    Tsakiridis, Nikolaos
    Ben-Dor, Eyal
    Theocharis, John
    Zalidis, George
    GEODERMA, 2019, 340 : 11 - 24