Xingming Zheng , Jia Zheng , Xigang Wang , Fuheng Qu , Tao Jiang , Zui Tao , Bo Zou , Shixu Song , Tianyu Ding
{"title":"An adaptive recognition method for crop row orientation in dry land by combining morphological and texture features","authors":"Xingming Zheng , Jia Zheng , Xigang Wang , Fuheng Qu , Tao Jiang , Zui Tao , Bo Zou , Shixu Song , Tianyu Ding","doi":"10.1016/j.still.2025.106576","DOIUrl":"10.1016/j.still.2025.106576","url":null,"abstract":"<div><div>Accurate identification of crop row orientation (CRO) is crucial for agricultural management. Most current CRO identification methods rely on image texture features from very-high-resolution (VHR) images, but their recognition accuracy still remains challenging, especially for large-scale mapping. To achieve rapid, cost-effective, and accurate large-scale CRO identification, an adaptive method was proposed. Vector cropland parcels generated on a cloud platform were combined with VHR imagery to adaptively identify CRO based on morphological and texture features. The effectiveness of the adaptive method was validated at Youyi Farm, Heilongjiang Province. The results are as follows: (1) A total of 4159 dry cropland parcels were extracted after removing paddy fields and a few non-cropland regions using the Normalized Difference Water Index (NDWI) and the Ratio Vegetation Index (RVI). The mean Intersection over Union (mIoU) was 70.5 %, and the EP (Extraction Precision) was 0.88, indicating that the overall parcel morphology generally aligns with the actual parcel shape. (2) By adjusting the parcel Length-to-Width ratio (L/W) to balance the CRO Recognition Rate (RR), Precision (Prec), and Root Mean Square Error (RMSE), an optimal L/W of 1.4 was determined, achieving the best overall balance. (3) Under the optimal L/W, the morphological feature method demonstrated a lower identification rate (RR: 67.3 %) but higher accuracy (Prec: 89 %) with a lower deviation (RMSE: 23.6°), while the texture feature method showed the opposite trend (RR: 89.4 %, Prec: 68 %, RMSE: 36.9°). Combining both features significantly improved the identification rate (RR: 94.7 %) while maintaining a low deviation (RMSE: 25.75°), indicating that the adaptive CRO identification method achieves optimal performance. The proposed method enables rapid and accurate CRO identification, supporting regional-scale CRO mapping.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106576"},"PeriodicalIF":6.1,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Peikun Li , Shengyan Ding , Xiuli Xin , Anning Zhu , Shunping Ding , Yu Mei , Yuan Liu , Xiaoyi Wu , Kaixin Lu , Qinghe Zhao
{"title":"Ecological niche differentiation of detritivores dominates soil mesofaunal community assembly in a 33-year fertilized cropland","authors":"Peikun Li , Shengyan Ding , Xiuli Xin , Anning Zhu , Shunping Ding , Yu Mei , Yuan Liu , Xiaoyi Wu , Kaixin Lu , Qinghe Zhao","doi":"10.1016/j.still.2025.106605","DOIUrl":"10.1016/j.still.2025.106605","url":null,"abstract":"<div><div>In agricultural ecosystems, long-term fertilization significantly alters soil mesofaunal diversity and composition. However, how fertilization shifts the relative contributions of deterministic and stochastic processes in the community assembly remains unclear. We examined mesofaunal co-occurrence networks, community assembly processes, and key drivers after 33 years of fertilization. Fertilization increased diversity, particularly among detritivores. Network analysis revealed that fertilization enhanced cooperative interactions within the mesofaunal networks. These interactions were more pronounced in networks associated with inorganic and mixed fertilizers compared to organic fertilizer, indicating a potential reduction in competitive and predatory pressures and an increase in mutualistic relationships among mesofaunal taxa. Detritivores exhibited higher network centrality, indicating their pivotal role in driving enhanced network cooperation and highlighting their critical importance in maintaining soil mesofaunal diversity in fertilized croplands. Fertilization drove the assembly of soil mesofaunal communities via a combination of deterministic and stochastic processes. The proportion of deterministic processes, such as heterogeneous selection, in the mesofaunal community assembly under inorganic fertilizer treatment was larger than that under organic fertilizer treatment, whereas stochastic processes were dominant in the unfertilized treatment. Detritivores exhibited a similar pattern in their assembly. Furthermore, our results revealed that both pH, as a crucial abiotic factor, and detritivore richness, serving as a pivotal biotic factor primarily influenced community assembly. Fertilization shaped soil mesofaunal communities via resource availability and ecological interactions. In summary, our research revealed the driving processes of 33-year fertilization on soil mesofaunal community assembly and the key guilds influencing these processes, providing insights into the mechanisms shaping and maintaining soil mesofaunal diversity in fertilized croplands.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106605"},"PeriodicalIF":6.1,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fei Chen , Li Yang , Tao Cui , Dongxing Zhang , Xiantao He , Kailiang Zhang , Zhimin Li
{"title":"Influence of the forward direction surface slope on the sowing depth operation performance of the mechanical profiling maize seeder","authors":"Fei Chen , Li Yang , Tao Cui , Dongxing Zhang , Xiantao He , Kailiang Zhang , Zhimin Li","doi":"10.1016/j.still.2025.106600","DOIUrl":"10.1016/j.still.2025.106600","url":null,"abstract":"<div><div>The change in the forward direction surface slope (FDSS) has a significant influence on the sowing depth operating performance (SDOP) of the mechanical profiling maize seeder sowing depth adjustment device (SDAD).This study analyses and identifies the main factors affecting the SDOP of the SDAD. RecurDyn simulation of FDSS and spring initial increment (SII) on SDAD downforce show that, taking the non-tilting state (NTS) as a benchmark, the increase in downforce does not exceed 7.29 % in the range from −25° to 0°. Within the range of 0° to 25°, the downforce decreases by 26.42 %. The Multi-body Dynamics and Discrete Element Method (MBD-DEM) coupled simulations of the impact of FDSS on SDOP show that as the absolute value of the FDSS increases, relative to the NTS,the average of sowing depth (ASD) changes by −10.34–6.33 %, the qualification rate of sowing depth (QRSD) changes by −41.21–6.78 %,the coefficient of variation of sowing depth (CVSD) changes by −2.23–2.99 %. Under different FDSS, as the SII increases and the operation speed (OS) decreases, the ASD increases from 38.52 mm to 54.91 mm, the QRSD increases from 10.56 % to 99.27 %, and the CVSD decreases from 17.32 % to 2.87 %. The field experiment results showed that the error between the simulation and field experiment results for the SDOP was less than 7 %. A mathematical model of the FDSS, SII and OS is established, make the SDOP under the FDSS converges to that of the NTS.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106600"},"PeriodicalIF":6.1,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jun Jiang , Feng Zhang , Enze Xie , Ruhai Wang , Yiyi Deng , Tianhua Feng , Xueqing Zhang , Xianli Xie , Renkou Xu
{"title":"In-situ and laboratory determined Ultisol-derived paddy soil pH varied with flooding condition in subtropical China","authors":"Jun Jiang , Feng Zhang , Enze Xie , Ruhai Wang , Yiyi Deng , Tianhua Feng , Xueqing Zhang , Xianli Xie , Renkou Xu","doi":"10.1016/j.still.2025.106608","DOIUrl":"10.1016/j.still.2025.106608","url":null,"abstract":"<div><div>Soil pH measured by laboratory standard method does not accurately reflect its actual acidity. In this study, we compared the pH values of anaerobic and aerobic farmland soils in Langxi, Yujiang, and Jinggangshan Counties in subtropical China, measured using <em>in-situ</em> and laboratory standard methods. The results showed that the <em>in-situ</em> pH values of anaerobic Ultisol-derived paddy soils were significantly higher than the laboratory values. Although there was an extremely significant correlation between the pH values obtained by the two methods (<em>R</em><sub><em>adj</em></sub><sup><em>2</em></sup>=0.15, <em>P</em> = 1.77 ×10<sup>−4</sup>, n = 81), extrapolating these results across different soil types proved challenging due to the specificity of paddy soils. The <em>in-situ</em> pH values of aerobic paddy soils were 0.52 units lower than the laboratory values, with an extremely significant correlation (<em>R</em><sub><em>adj</em></sub><sup><em>2</em></sup>=0.67, <em>P</em> = 5.95 ×10⁻²¹, n = 81). <em>In-situ</em> pH mapping of farmland soils under both anaerobic and aerobic conditions revealed that the paddy soils in northwest Jinggangshan County, along with the majority of aerobic paddy soils in the study areas, exhibited acidification and aluminum-induced phytotoxicity. These findings provide valuable insights into estimating the <em>in-situ</em> soil pH of paddy soils under anaerobic and aerobic rotations, providing a more accurate and efficient representation of actual soil pH conditions during different cultivation stages in the acidic paddy soil regions of southern China.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106608"},"PeriodicalIF":6.1,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiajun Wu , Zichuan Li , Yong Li , Jiawen Liu , Cheng Liu , Yanjun Chai , Chao Ai , Qaiser Hussain , Marios Drosos , Shengdao Shan
{"title":"Effects of rice straw biochar application rates on soil aggregate biogeochemistry and linkages to microbial community structure and enzyme activities","authors":"Jiajun Wu , Zichuan Li , Yong Li , Jiawen Liu , Cheng Liu , Yanjun Chai , Chao Ai , Qaiser Hussain , Marios Drosos , Shengdao Shan","doi":"10.1016/j.still.2025.106589","DOIUrl":"10.1016/j.still.2025.106589","url":null,"abstract":"<div><div>Biochar, a widely adopted soil amendment, has been widely recognized for its potential to improve crop yields and soil nutrients significantly. This enhancement is primarily attributed to the crucial role of soil microorganisms, whose contribution to soil fertility is significant and often underappreciated. However, the effects of varying biochar application rates on soil functional biota, particularly within aggregates that expand soil spatial heterogeneity, remain unclear. Understanding the relationship between nutrient dynamics and microbial community composition in these aggregates is essential for comprehending the intricate connections between soil microbiomes and related biogeochemical cycles. This study utilized long-term experimental soils, including treatments with no fertilizer, chemical fertilizer alone, and chemical fertilizer combined with rice straw biochar at gradient application rates (22.5, 45, 90 t·hm<sup>−2</sup>). The responses of microbial community structure and soil enzyme activities in whole soil and aggregates to different biochar application rates were investigated. Results showed that, compared to NPK treatment, biochar significantly increased bacterial and fungal diversity in macroaggregates. It also notably increased the relative abundance of <em>Proteobacteria</em> and <em>Ascomycota</em> in soil and aggregates, and at the same time reduced the relative abundance of <em>Chloroflexi</em> and <em>Basidiomycota</em>. Furthermore, carbon and phosphorus cycle-related enzyme activities increased significantly with higher biochar application rates. However, the activity of NAG, a nitrogen cycle-related enzyme, decreased as biochar application increased. Mantel analysis revealed that the relationship between microorganisms, enzyme activity, and soil nutrients was closest at a biochar application rate of 45 t·hm<sup>−2</sup>. Structural equation modeling demonstrated that macroaggregates exhibited the most complex nutrient accumulation relationships, with bacterial and fungal diversity promoting nutrient accumulation. In conclusion, moderate biochar application induced the most intricate and closely connected microbial networks in macroaggregates, promoting soil nutrient cycling.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106589"},"PeriodicalIF":6.1,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhengxin Zhao , Zongyang Li , Yao Li , Xuegui Zhang , Xiaobo Gu , Huanjie Cai
{"title":"Exploring and predicting nitrogen fertilizer use efficiency of maize (Zea mays L.)-soybean (Glycine max (L.) Merr.) intercropping systems in China: A combined Meta-analysis and machine learning approach","authors":"Zhengxin Zhao , Zongyang Li , Yao Li , Xuegui Zhang , Xiaobo Gu , Huanjie Cai","doi":"10.1016/j.still.2025.106603","DOIUrl":"10.1016/j.still.2025.106603","url":null,"abstract":"<div><div>Maize <strong>(Zea mays L.)</strong>-soybean <strong>(Glycine max (L.) Merr.)</strong> intercropping systems have been widely promoted in China due to their potential to enhance agricultural land use efficiency through crop complementarity. However, the complex interactions between environmental conditions and management practices create significant challenges for understanding and accurately predicting nitrogen (N) use efficiency under different production conditions. Through a meta-analysis of 330 datasets from 45 experimental sites across China and machine learning approaches, we evaluated the fertilizer N equivalent ratio (FNER) and developed a prediction model for it in maize-soybean intercropping systems. The national average FNER value of maize-soybean intercropping systems in China was 1.41 ± 0.02. The FNER of maize-soybean intercropping systems was significantly correlated with climate conditions, the proportion of maize, N application rate, and temporal niche differentiation (TND). Regions with higher annual precipitation and temperature showed a greater N fertilizer utilization advantage in maize-soybean intercropping. Furthermore, reducing N application rate and the proportion of maize while extending TND can enhance the FNER of maize-soybean intercropping systems. N application rate and TND were identified as the most important input parameters for machine learning-based FNER prediction in maize-soybean intercropping systems. Among the machine learning models, Random Forest and Gradient Boosting models demonstrated superior effectiveness in predicting FNER values using five input variables, including N application rate, TND, soil organic matter content, average annual temperature, and soybean planting density. The current study can provide practical guidance for improving the N use efficiencies of maize-soybean intercropping systems and offer a robust tool for predicting FNER under various environmental and management conditions.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106603"},"PeriodicalIF":6.1,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hamid Mohebzadeh , Asim Biswas , Ben DeVries , Ramesh Rudra , Wanhong Yang , Prasad Daggupati
{"title":"Integrating genetic algorithm with AnnAGNPS for optimizing BMPs placement to reduce sheet/rill and ephemeral gully erosion","authors":"Hamid Mohebzadeh , Asim Biswas , Ben DeVries , Ramesh Rudra , Wanhong Yang , Prasad Daggupati","doi":"10.1016/j.still.2025.106598","DOIUrl":"10.1016/j.still.2025.106598","url":null,"abstract":"<div><div>In order to effectively reduce nonpoint source pollutants in agricultural areas within a watershed, a combination of Best Management Practices (BMPs) is selected based on their economic and environmental effectiveness. However, determining the optimal combination can be challenging due to the implementation costs and the consideration of decision makers' preferences. This research presents a methodology for integrating a genetic algorithm with the Annualized Agricultural Non-Point Source Pollution model (AnnAGNPS) to effectively select the most efficient BMPs placement for a given watershed. By optimizing BMPs placement, the model can minimize sediment loads from different types of erosion, including sheet/rill, ephemeral gully, and total erosion at the minimal cost. Results demonstrated that BMP placement by the optimization model reduced sediment load caused by sheet/rill by 84.6 %, ephemeral gully by 85.4 %, and total erosion by 86.3 % in the study watershed. Additionally, the model achieved these results at a minimal cost, making it a cost-effective solution for sediment load reduction in the watershed. Also, the results showed the effective implementation of the developed optimization approach for strategically locating BMPs in specific areas, rather than implementing them throughout the entire watershed. By targeting these areas and implementing suitable BMPs, the model was able to reduce the amount of sediment load and remain cost-effective. The proposed weighted overlay technique helped to place BMPs within agricultural fields instead of AnnAGNPS cells, making it easier for farmers to adopt and effectively reduce sediment load in each field. The developed model in the current study can be applied by decision makers in other watersheds with limited resources for implementing BMPs.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106598"},"PeriodicalIF":6.1,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Long-term straw return with nitrogen fertilization enhances soil pore structure, POM accumulation, and their positive feedback in a Vertisol","authors":"Tianyu Ding , Zichun Guo , Wei Li , Xinhua Peng","doi":"10.1016/j.still.2025.106602","DOIUrl":"10.1016/j.still.2025.106602","url":null,"abstract":"<div><div>Soil pore structure determines particulate organic matter (POM) decomposition by influencing water and gas transport. The accumulation of POM due to nitrogen (N) fertilization has been reported in many studies. However, the effects of N fertilization and straw management on POM and pores as well as the relationship between these two factors remain inconclusive. Therefore, a 15-year (2008–2023) N fertilization field experiment was conducted on a Vertisol, covering three N application rates (0, 360, and 540 kg ha<sup>−1</sup> year<sup>−1</sup>, designated as N0, N360, and N540) and straw management (straw return and straw removal) in a wheat-maize cropping system. X-ray computed tomography (CT) was utilized to quantify the pore structure, and POM was classified into fresh POM and decomposed POM based on their morphological characteristics. The findings revealed that straw return treatment increased fresh POM by 3.08–3.77-fold at N0, N360 and N540 rates, along with enhancements in image-based porosity (>50 μm in diameter, Ø), connected porosity, connection probability at the N540 rate compared to straw removal (<em>P</em> < 0.05). Under straw return conditions, the N360 treatment notably increased fresh POM by 2.3-fold compared to the N0 treatment; the N540 treatment led to a 2.94-fold increase in fresh POM and a 1.16-fold increase in decomposed POM (<em>P</em> < 0.05). The N540 treatment also increased image-based porosity, connected porosity, surface area density, mean compactness, and decreased mean pore distance (<em>P</em> < 0.05). Furthermore, with straw return conditions, connected pores were identified as the primary site for fresh POM distribution, accounting for a distribution proportion of 26.9 %-77.9 %. Notably, POM exhibited a positive correlation with > 200 μm Ø porosity under straw return treatment (<em>P</em> < 0.05), whereas no significant relationship was observed between POM and pore structure under straw removal (<em>P</em> > 0.05). Overall, our findings indicate that long-term N fertilization (N360 and N540) coupled with straw return facilitates POM accumulation, particularly fresh POM, and enhances soil pore structure in Vertisol.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106602"},"PeriodicalIF":6.1,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Liu Mochen , Yang Kuankuan , Yan Yinfa , Song Zhanhua , Tian Fuyang , Li Fade , Yu Zhenwei , Rongyao Zhang , Yang Qinglu , Lu Yao
{"title":"Multi-spectral evaluation of total nitrogen, phosphorus and potassium content in soil using Vis-NIR spectroscopy based on a modified support vector machine with whale optimization algorithm","authors":"Liu Mochen , Yang Kuankuan , Yan Yinfa , Song Zhanhua , Tian Fuyang , Li Fade , Yu Zhenwei , Rongyao Zhang , Yang Qinglu , Lu Yao","doi":"10.1016/j.still.2025.106567","DOIUrl":"10.1016/j.still.2025.106567","url":null,"abstract":"<div><div>Accurate and non-destructive detection of total nitrogen (TN), total phosphorus (TP), and total potassium (TK) levels in soil is crucial for precise soil testing and fertilization in modernized precision agriculture. Traditional methods for soil composition analysis are expensive, time-consuming, and destructive. This research aims to establish a low-cost, high-precision, and non-destructive method for soil nutrient detection based on visible-near-infrared (Vis-NIR) spectroscopy (350–2500 nm) combined with improved machine learning algorithms. The Vis-NIR spectra of soil samples were acquired using the RS-5400 high-resolution ground feature spectrometer. Subsequently, the Monte Carlo sampling cross-validation (MCCV) algorithm was used to eliminate abnormal samples, and then different preprocessing methods were performed on the spectral data including first-derivative (FD), Savitzky-Golay smoothing (SG) and others. The optimal preprocessing method was selected from these options. In order to remove redundant information and increase the speed of calculation, five algorithms such as competitive adaptive reweighted sampling (CARS), iteratively retains informative variables (IRIV) and the variable iterative space shrinkage approach (VISSA)-IRIV algorithm were used to select feature variables. The characteristic wavelengths closely related to TN, TP, and TK in the soil have been extracted. Then, the RBF kernel (radial basis function) and poly kernel were mixed to obtain the RBF-poly hybrid kernel function, and then the hybrid kernel function support vector machine (RBF-poly-SVM) and the radial basis kernel function support vector machine (RBF-SVM) were applied respectively. Establish prediction models and introduce the whale optimization algorithm (WOA) to optimize the <em>g</em> (kernel function parameter), <em>c</em> (penalty factor) and k<sub><em>-rbf</em></sub> (weight coefficient) parameters in the two models. The performance of the developed models was tested using the coefficient of determination (<em>R</em><sup><em>2</em></sup>), the root mean squared error (<em>RMSE</em>) and the ratio of performance to deviation (<em>RPD</em>). The results demonstrated that among all models, the RBF-poly -SVM modeling methods were superior to the RBF-SVM model. The best results for estimation of TN, TP, and TK elements were achieved by the models of SG-square-FD + IRIV + RBF-poly-SVM (<em>R</em><sup><em>2</em></sup><sub><em>C</em></sub>=0.960, <em>R</em><sup><em>2</em></sup><sub><em>V</em></sub>=0.902, <em>RPD</em>=3.206), square-FD + IRIV + RBF-poly-SVM (<em>R</em><sup><em>2</em></sup><sub><em>C</em></sub>=0.999, <em>R</em><sup><em>2</em></sup><sub><em>V</em></sub>=0.937, <em>RPD</em>=3.939), square root + VISSA-IRIV + RBF-poly-SVM (<em>R</em><sup><em>2</em></sup><sub><em>C</em></sub>=0.955, <em>R</em><sup><em>2</em></sup><sub><em>V</em></sub>=0.904, <em>RPD</em>=2.608), respectively. The findings of the current approach own practical implications","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106567"},"PeriodicalIF":6.1,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Qiyong Zhang , Yuzhen Kong , Qingliang Wu , Man Hu
{"title":"Influence of potassium salt on cracking behavior of purple soil under wetting–drying cycles","authors":"Qiyong Zhang , Yuzhen Kong , Qingliang Wu , Man Hu","doi":"10.1016/j.still.2025.106599","DOIUrl":"10.1016/j.still.2025.106599","url":null,"abstract":"<div><div>The cracking behavior of purple soil during wetting-drying cycles is a common natural phenomenon in subtropical monsoon regions, posing risks of soil erosion and geological hazards such as landslides. The addition of salts changes the physicochemical properties of purple soil, which has a significant influence on the crack dynamics. Traditionally, NaCl is employed as a representative salt to investigate its influence on crack development during drying. However, NaCl is not the only prevalent salt in natural environments. In the humid and rainy, Sichuan Basin, where fertile purple soil predominates, potassium-based fertilizers, unlike NaCl, are widespread. Therefore, this study explores the effect of potassium salts (i.e., KCl, K<sub>2</sub>SO<sub>4</sub>, and plant ash) on cracking behavior of purple soil subjected to wetting–drying cycles. To achieve this, a combination of laboratory experiments, long-term monitoring, advanced image analysis techniques, and microscopic characterization is employed. The results indicate that KCl reduces crack formation, while K₂SO₄ enhances it compared to the salt-free sample after the first wetting-drying cycle. A small amount of plant ash (0.3 %–1.0 %) promotes cracking, whereas a higher content (2.0 %–3.0 %) suppresses it. As the number of wetting-drying cycles increases from one to twelve, the total crack length in most samples initially increases, peaking at 336–476 cm, before decreasing to 262–391 cm. In contrast, in samples with 2.0 %-3.0 % KCl, it decreases directly from 125 to 292 cm to 4–223 cm, but may temporarily increase after several cycles. The type and content of potassium salts exert a significant influence on cracking behavior, primarily governed by ion exchange reactions in montmorillonite, alterations in matric suction, shifts in mineral composition, and salt weathering.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106599"},"PeriodicalIF":6.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}