Smart farming revolution: Leveraging machine learning for sustainable agriculture

IF 10 1区环境科学与生态学 Q1 ENGINEERING, ENVIRONMENTAL

Journal of Cleaner Production Pub Date : 2025-09-29 DOI:10.1016/j.jclepro.2025.146434

Weiye Wang , Qing Li

{"title":"Smart farming revolution: Leveraging machine learning for sustainable agriculture","authors":"Weiye Wang , Qing Li","doi":"10.1016/j.jclepro.2025.146434","DOIUrl":null,"url":null,"abstract":"<div><h3>Problem</h3><div>In today's world, agriculture faces several challenges, including environmental degradation, crop diseases, and ineffective resource utilization. These challenges affect sustainability as well as food security.</div></div><div><h3>Method</h3><div>ology: In order to address the above-mentioned problems, several machine learning (ML) approaches, namely, Convolutional Neural Network (CNN), Random Forest (RF), Long Short Term Memory (LSTM), and other deep neural models, were used. These techniques aid in maximizing resource allocation, improving climate resilience, and enhancing early disease detection in agricultural ecosystems. Data for this study were collected through a questionnaire survey from 847 farmers across three main regions of China and were filtered using random sampling. Moreover, the collected data were analyzed through the Statistical Package for the Social Sciences (SPSS).</div></div><div><h3>Results</h3><div>The ML-based technique improved productivity, reduced operational costs, and enhanced sustainability. It attained a 20 % crop yield increase, minimized water consumption by 15 %, and reduced pesticide costs by $5000 per year in comparison to conventional farming practices.</div></div><div><h3>Impact</h3><div>This study shows the ability of ML technologies to revolutionize traditional agriculture, fostering stronger and sustainable agriculture systems that can sustain contemporary demands without compromising ecological and economic stability.</div></div>","PeriodicalId":349,"journal":{"name":"Journal of Cleaner Production","volume":"527 ","pages":"Article 146434"},"PeriodicalIF":10.0000,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cleaner Production","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0959652625017846","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}

引用次数: 0

Abstract

Problem

In today's world, agriculture faces several challenges, including environmental degradation, crop diseases, and ineffective resource utilization. These challenges affect sustainability as well as food security.

Method

ology: In order to address the above-mentioned problems, several machine learning (ML) approaches, namely, Convolutional Neural Network (CNN), Random Forest (RF), Long Short Term Memory (LSTM), and other deep neural models, were used. These techniques aid in maximizing resource allocation, improving climate resilience, and enhancing early disease detection in agricultural ecosystems. Data for this study were collected through a questionnaire survey from 847 farmers across three main regions of China and were filtered using random sampling. Moreover, the collected data were analyzed through the Statistical Package for the Social Sciences (SPSS).

Results

The ML-based technique improved productivity, reduced operational costs, and enhanced sustainability. It attained a 20 % crop yield increase, minimized water consumption by 15 %, and reduced pesticide costs by $5000 per year in comparison to conventional farming practices.

Impact

This study shows the ability of ML technologies to revolutionize traditional agriculture, fostering stronger and sustainable agriculture systems that can sustain contemporary demands without compromising ecological and economic stability.

查看原文本刊更多论文

智能农业革命：利用机器学习实现可持续农业

当今世界，农业面临着环境退化、作物病害和资源利用效率低下等诸多挑战。这些挑战影响到可持续性和粮食安全。方法：为了解决上述问题，使用了几种机器学习（ML）方法，即卷积神经网络（CNN）、随机森林（RF）、长短期记忆（LSTM）和其他深度神经模型。这些技术有助于最大限度地分配资源，提高气候适应能力，并加强农业生态系统的早期疾病检测。本研究的数据是通过对中国三个主要地区的847名农民进行问卷调查收集的，并采用随机抽样方法进行过滤。此外，收集的数据通过社会科学统计软件包（SPSS）进行分析。结果基于ml的技术提高了生产效率，降低了运营成本，增强了可持续性。与传统耕作方式相比，它使作物产量增加了20%，用水量减少了15%，每年减少了5000美元的农药成本。这项研究表明，机器学习技术能够彻底改变传统农业，培育更强大、更可持续的农业系统，在不影响生态和经济稳定的情况下，满足当代需求。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Cleaner Production 环境科学-工程：环境

CiteScore

20.40

自引率

9.00%

发文量

4720

审稿时长

111 days

期刊介绍： The Journal of Cleaner Production is an international, transdisciplinary journal that addresses and discusses theoretical and practical Cleaner Production, Environmental, and Sustainability issues. It aims to help societies become more sustainable by focusing on the concept of 'Cleaner Production', which aims at preventing waste production and increasing efficiencies in energy, water, resources, and human capital use. The journal serves as a platform for corporations, governments, education institutions, regions, and societies to engage in discussions and research related to Cleaner Production, environmental, and sustainability practices.