Enhanced Hyperspectral Forest Soil Organic Matter Prediction Using a Black-Winged Kite Algorithm-Optimized Convolutional Neural Network and Support Vector Machine
Soil Organic Matter (SOM) is crucial for soil fertility, and effective detection methods are of great significance for the development of agriculture and forestry. This study uses 206 hyperspectral soil samples from the state-owned Yachang and Huangmian Forest Farms in Guangxi, using the SPXY algori...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/503 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589246805835776 |
|---|---|
| author | Yun Deng Lifan Xiao Yuanyuan Shi |
| author_facet | Yun Deng Lifan Xiao Yuanyuan Shi |
| author_sort | Yun Deng |
| collection | DOAJ |
| description | Soil Organic Matter (SOM) is crucial for soil fertility, and effective detection methods are of great significance for the development of agriculture and forestry. This study uses 206 hyperspectral soil samples from the state-owned Yachang and Huangmian Forest Farms in Guangxi, using the SPXY algorithm to partition the dataset in a 4:1 ratio, to provide an effective spectral data preprocessing method and a novel SOM content prediction model for the study area and similar regions. Three denoising methods (no denoising, Savitzky–Golay filter denoising, and discrete wavelet transform denoising) were combined with nine mathematical transformations (original spectral reflectance (R), first-order differential (1DR), second-order differential (2DR), MSC, SNV, logR, (logR)′, 1/R, ((1/R)′) to form 27 combinations. Through Pearson heatmap analysis and modeling accuracy comparison, the SG-1DR preprocessing combination was found to effectively highlight spectral data features. A CNN-SVM model based on the Black Kite Algorithm (BKA) is proposed. This model leverages the powerful parameter tuning capabilities of BKA, uses CNN for feature extraction, and uses SVM for classification and regression, further improving the accuracy of SOM prediction. The model results are RMSE = 3.042, R<sup>2</sup> = 0.93, MAE = 4.601, MARE = 0.1, MBE = 0.89, and PRIQ = 1.436. |
| format | Article |
| id | doaj-art-2f0408a7bbcb45ee82d05a59955766e1 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-2f0408a7bbcb45ee82d05a59955766e12025-01-24T13:19:38ZengMDPI AGApplied Sciences2076-34172025-01-0115250310.3390/app15020503Enhanced Hyperspectral Forest Soil Organic Matter Prediction Using a Black-Winged Kite Algorithm-Optimized Convolutional Neural Network and Support Vector MachineYun Deng0Lifan Xiao1Yuanyuan Shi2College of Computer Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaCollege of Computer Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaKey Laboratory of Central South Fast-Growing Timber Cultivation of Forestry Ministry of China, Guangxi Forestry Research Institute, Nanning 530002, ChinaSoil Organic Matter (SOM) is crucial for soil fertility, and effective detection methods are of great significance for the development of agriculture and forestry. This study uses 206 hyperspectral soil samples from the state-owned Yachang and Huangmian Forest Farms in Guangxi, using the SPXY algorithm to partition the dataset in a 4:1 ratio, to provide an effective spectral data preprocessing method and a novel SOM content prediction model for the study area and similar regions. Three denoising methods (no denoising, Savitzky–Golay filter denoising, and discrete wavelet transform denoising) were combined with nine mathematical transformations (original spectral reflectance (R), first-order differential (1DR), second-order differential (2DR), MSC, SNV, logR, (logR)′, 1/R, ((1/R)′) to form 27 combinations. Through Pearson heatmap analysis and modeling accuracy comparison, the SG-1DR preprocessing combination was found to effectively highlight spectral data features. A CNN-SVM model based on the Black Kite Algorithm (BKA) is proposed. This model leverages the powerful parameter tuning capabilities of BKA, uses CNN for feature extraction, and uses SVM for classification and regression, further improving the accuracy of SOM prediction. The model results are RMSE = 3.042, R<sup>2</sup> = 0.93, MAE = 4.601, MARE = 0.1, MBE = 0.89, and PRIQ = 1.436.https://www.mdpi.com/2076-3417/15/2/503optimization algorithmorganic matter contentspectral data processingforest soilGuangxi |
| spellingShingle | Yun Deng Lifan Xiao Yuanyuan Shi Enhanced Hyperspectral Forest Soil Organic Matter Prediction Using a Black-Winged Kite Algorithm-Optimized Convolutional Neural Network and Support Vector Machine Applied Sciences optimization algorithm organic matter content spectral data processing forest soil Guangxi |
| title | Enhanced Hyperspectral Forest Soil Organic Matter Prediction Using a Black-Winged Kite Algorithm-Optimized Convolutional Neural Network and Support Vector Machine |
| title_full | Enhanced Hyperspectral Forest Soil Organic Matter Prediction Using a Black-Winged Kite Algorithm-Optimized Convolutional Neural Network and Support Vector Machine |
| title_fullStr | Enhanced Hyperspectral Forest Soil Organic Matter Prediction Using a Black-Winged Kite Algorithm-Optimized Convolutional Neural Network and Support Vector Machine |
| title_full_unstemmed | Enhanced Hyperspectral Forest Soil Organic Matter Prediction Using a Black-Winged Kite Algorithm-Optimized Convolutional Neural Network and Support Vector Machine |
| title_short | Enhanced Hyperspectral Forest Soil Organic Matter Prediction Using a Black-Winged Kite Algorithm-Optimized Convolutional Neural Network and Support Vector Machine |
| title_sort | enhanced hyperspectral forest soil organic matter prediction using a black winged kite algorithm optimized convolutional neural network and support vector machine |
| topic | optimization algorithm organic matter content spectral data processing forest soil Guangxi |
| url | https://www.mdpi.com/2076-3417/15/2/503 |
| work_keys_str_mv | AT yundeng enhancedhyperspectralforestsoilorganicmatterpredictionusingablackwingedkitealgorithmoptimizedconvolutionalneuralnetworkandsupportvectormachine AT lifanxiao enhancedhyperspectralforestsoilorganicmatterpredictionusingablackwingedkitealgorithmoptimizedconvolutionalneuralnetworkandsupportvectormachine AT yuanyuanshi enhancedhyperspectralforestsoilorganicmatterpredictionusingablackwingedkitealgorithmoptimizedconvolutionalneuralnetworkandsupportvectormachine |