[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121008-en":3,"doc-seo-121008-105":30,"detail-sidebar-cat-0-en-105":95},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121008,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Machine learning for chemical-humus correlation in soil - key covariates analysis","Machine learning is applied to model how quantitative humus content in soil depends on phosphate (P₂O₅), potassium oxide (K₂O), hydrolytic acid, and pH values in both aqueous and saline environments. Linear regression is selected for its suitability to a limited dataset and for interpretability. Model performance is quantified with MAE=0.517, MSE=0.460, and cross-validated determination coefficient reaching 0.685, supporting robust predictive power. Feature importance assessment highlights hydrolytic acid as the most impactful covariate through its effects on microbial activity and soil metabolism.","Machine learning for chemical-humus correlation in soil  \nIvan Lebedev 1*  \n1 Moscow Aviation Institute (National Research University), 125993, Volokolamskoe shosse, 4, Moscow, Russia  \nAbstract. This article investigates the dependency of the quantitative content of humus in soil on phosphate (P₂O₅), potassium oxide (K₂O), hydrolytic acid, as well as the pH value in aqueous and saline environments through machine learning. Linear regression was chosen as the primary model. The mean absolute error (MAE) was found to be 0.517, mean squared error (MSE)– 0.460, and the coefficient of determination after cross-validation reached 0.685. The search for the most significant covariate among the listed ones identified hydrolytic acid as the most impactful due  \nto its influence on microbial activity in the soil and metabolism.  \n1 Introduction  \nIn recent years, there has been a significant growth in interest in applying machine learning methods across various scientific and practical fields, opening new perspectives for analyzing and interpreting complex data. The integration of these technologies in agrochemistry, where they can play a crucial role in optimizing agricultural production and sustainable soil resource management, is particularly noteworthy. One of the main aspects in this area is predicting the humus content in the soil, which is crucial for assessing its fertility as humus directly affects the physical, chemical, and biological properties of the soil, determining its water retention capacity, structure, nutrient composition, and microbial activity.  \nThe analysis of correlations between soil chemical indicators, such as phosphorus and potassium content, acidity levels, and others, and humus levels using machine learning methods forms the basis for developing effective prediction models. These models can adapt to changing conditions and the specifics of different soil types. Such models become an indispensable tool for agronomists and farmers, providing them with information for making decisions on soil treatment, fertilization, and crop rotation plans aimed at increasing yield and maintaining the ecological balance in agricultural ecosystems [1-3] . This approach can complement field analysis using satellite imagery [4] and unmanned aerial vehicles [5] .  \n2 Materials and Methods  \nIn the conducted research, 70 soil samples were selected for comprehensive chemical analysis to determine key parameters, including concentrations of phosphate (P₂O₅),  \nΎ Corresponding author: [lebedev.ivan.ig@yandex.ru](lebedev.ivan.ig@yandex.ru)  \n© The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)).  \npotassium oxide (K₂O), hydrolytic acid, as well as pH values in aqueous and saline environments and humus content. Given the relatively small data sample size, the application of deep learning models was deemed impractical due to their tendency to overfit in limited dataset conditions. Instead, linear regression was chosen as a method demonstrating high efficiency with small and medium data volumes and capable of providing good result interpretability. Linear regression establishes linear dependencies between independent variables (chemical indicators) and the dependent variable (humus content) .  \nAfter training the model, the following performance indicators were obtained: the mean absolute error (MAE) was 0.517, the mean squared error (MSE) was 0.460, and the coefficient of determination (R² score) reached 0.668. The mean absolute error reflects the average deviation of predicted values from actual ones, providing an understanding of the overall accuracy of the model in absolute terms. The mean squared error, being the square of the difference between predicted and real values, penalizes large errors more severely than small ones, serving as an indic","cbCaikxnF6Hu1ABc","https://ap.wps.com/l/cbCaikxnF6Hu1ABc","pdf",438093,1,6,"English","en",105,"# Introduction\n## Relevance of humus prediction in agrochemistry\n## Machine learning for soil chemical indicator correlations\n# Materials and Methods\n## Dataset and chemical parameters\n## Model choice: linear regression\n## Metrics and cross-validation\n## Random forest feature importance","[{\"question\":\"Which soil variables are used to predict humus content?\",\"answer\":\"The study uses phosphate (P₂O₅), potassium oxide (K₂O), hydrolytic acid, and pH values in aqueous and saline environments, together with measured humus content.\"},{\"question\":\"Why is linear regression chosen instead of deep learning?\",\"answer\":\"Deep learning is considered impractical because the dataset is relatively small and would likely overfit; linear regression offers efficiency with small/medium data and better interpretability.\"},{\"question\":\"How is the model performance evaluated?\",\"answer\":\"Performance is assessed using MAE, MSE, and the coefficient of determination (R²), with additional robustness verified by cross-validation reaching 0.685.\"},{\"question\":\"Which covariate is identified as the most significant for humus and why?\",\"answer\":\"Hydrolytic acid is found to be the most impactful, attributed to its influence on microbial activity in soil and related metabolism processes.\"}]","Machine learning for chemical-humus correlation in soil - key covariates analysis | PDF",1785733285,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"machine-learning-for-chemical-humus-correlation-in-soil-key-covariates-analysis","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-for-chemical-humus-correlation-in-soil-key-covariates-analysis/121008/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"Which soil variables are used to predict humus content?","Question",{"text":75,"@type":76},"The study uses phosphate (P₂O₅), potassium oxide (K₂O), hydrolytic acid, and pH values in aqueous and saline environments, together with measured humus content.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is linear regression chosen instead of deep learning?",{"text":80,"@type":76},"Deep learning is considered impractical because the dataset is relatively small and would likely overfit; linear regression offers efficiency with small/medium data and better interpretability.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the model performance evaluated?",{"text":84,"@type":76},"Performance is assessed using MAE, MSE, and the coefficient of determination (R²), with additional robustness verified by cross-validation reaching 0.685.",{"name":86,"@type":73,"acceptedAnswer":87},"Which covariate is identified as the most significant for humus and why?",{"text":88,"@type":76},"Hydrolytic acid is found to be the most impactful, attributed to its influence on microbial activity in soil and related metabolism processes.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,118,123,126,131,134,138],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},"Technology",50,"technology",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":124,"slug":125},30,"research-report",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":129,"slug":130},9,"Religion & Spirituality",20,"religion-spirituality",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":129,"slug":133},"World Cup","world-cup",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":135,"slug":137},10,"Lifestyle","lifestyle",{"id":139,"doc_module":4,"doc_module_name":46,"category_name":140,"show_sort_weight":110,"slug":141},19,"General","general"]