Zhong Kangyuan, Li Yane, Huan Weiwei, Weng Xiang, Wu Bin, Chen Zheyi, Liang Hao, Feng Hailin
College of Mathematics and Computer science, Zhejiang A&F University, Hangzhou, 311300, China; Key Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou, 311300, China; Key Laboratory of Forestry Perception Technology and Intelligent Equipment State Forestry Administration, Hangzhou, 311300, China.
College of Chemistry and Materials Engineering, Zhejiang A&F University, Hangzhou, 311300, China.
Spectrochim Acta A Mol Biomol Spectrosc. 2024 Jul 5;315:124259. doi: 10.1016/j.saa.2024.124259. Epub 2024 Apr 10.
Soil is the basis of agricultural production and accessing accurate information on soil nutrients is essential. Traditional methods of soil composition detection, which are based on chemical analysis, are characterized by being costly and polluting. Spectroscopic analysis has proven to be a rapid, non-destructive and effective technique for predicting soil properties in general and potassium, phosphorus and organic matter in particular. However, previous research on soils has rarely combined optimization algorithms with machine learning techniques, which has led to suboptimal model accuracy and convergence speed. In this study, a total of 184 soil samples were collected from three cities of Linhai, Yueqing and Longyou County, Zhejiang Province, China. After measuring pH values, alkali-hydrolyzable nitrogen (SAN), available phosphorus (SAP), available potassium (SAK) and soil organic matter (SOM) contents, along with their corresponding spectroscopic measurements, nine pretreatment methods and their combinations are adopted. A novel assessment model, integrating support vector machine and dung beetle optimization algorithm (DBO-SVR), is proposed to predict pH values and SAN, SAP, SAK, SOM content. Meanwhile, the DBO algorithm is compared with three mainstream optimization algorithms (particle swarm optimization (PSO), whale optimization algorithm (WOA) and grey wolf optimizer (GWO)). Results showed that the DBO-SVR model was shown best performance with R, RMSEP and RPD of 0.9842, 0.1306, 5.6485 respectively for prediction of pH value, with R, RMSEP and RPD of 0.8802, 15.0574 mg/kg and 2.0508, respectively for assessment of SAN content, with R, RMSEP and RPD of 0.9790, 12.8298 mg/kg, and 4.5132, respectively for assessment of SAP content, with R, RMSEP and RPD of 0.8677, 22.5107 mg/kg, and 1.9546, respectively for assessment of SAK content, and with R, RMSEP and RPD of 0.9273, 2.6427g/kg , and 2.1821, respectively for assessment of SOM content. This study demonstrates that the combination of near-infrared (NIR) spectroscopy and the DBO-SVR algorithm is capable of predicting soil nutrient composition with greater accuracy and efficiency.
土壤是农业生产的基础，获取准确的土壤养分信息至关重要。基于化学分析的传统土壤成分检测方法成本高且有污染。光谱分析已被证明是一种快速、无损且有效的技术，可用于总体预测土壤性质，尤其是钾、磷和有机质。然而，以往对土壤的研究很少将优化算法与机器学习技术相结合，导致模型精度和收敛速度不理想。本研究从中国浙江省临海市、乐清市和龙游县三个城市共采集了184个土壤样本。在测量了pH值、碱解氮（SAN）、有效磷（SAP）、速效钾（SAK）和土壤有机质（SOM）含量以及相应的光谱测量值后，采用了九种预处理方法及其组合。提出了一种集成支持向量机和蜣螂优化算法（DBO-SVR）的新型评估模型，用于预测pH值以及SAN、SAP、SAK、SOM含量。同时，将DBO算法与三种主流优化算法（粒子群优化算法（PSO）、鲸鱼优化算法（WOA）和灰狼优化器（GWO））进行了比较。结果表明，DBO-SVR模型在预测pH值时表现最佳，R、RMSEP和RPD分别为0.9842、0.1306、5.6485；评估SAN含量时，R、RMSEP和RPD分别为0.8802、15.0574mg/kg和2.0508；评估SAP含量时，R、RMSEP和RPD分别为0.9790、12.8298mg/kg和4.5132；评估SAK含量时，R、RMSEP和RPD分别为0.8677、22.5107mg/kg和1.9546；评估SOM含量时，R、RMSEP和RPD分别为0.9273、2.6427g/kg和2.1821。本研究表明，近红外（NIR）光谱与DBO-SVR算法相结合能够更准确、高效地预测土壤养分组成。
