气候变化领域集成服务门户(CCPortal): Predicting environmental impacts of smallholder wheat production by coupling life cycle assessment and machine learning

CCPortal

DOI	10.1016/j.scitotenv.2024.171097
	Predicting environmental impacts of smallholder wheat production by coupling life cycle assessment and machine learning
	Yu, Chunxiao; Xu, Gang; Cai, Ming; Li, Yuan; Wang, Lijia; Zhang, Yan; Lin, Huilong
发表日期	2024
ISSN	0048-9697
EISSN	1879-1026
起始页码	921
卷号	921
英文摘要	Wheat grain production is a vital component of the food supply produced by smallholder farms but faces significant threats from climate change. This study evaluated eight environmental impacts of wheat production using life cycle assessment based on survey data from 274 households, then built random forest models with 21 input features to contrast the environmental responses of different farming practices across three shared socioeconomic pathways (SSPs), spanning from 2024 to 2100. The results indicate significant environmental repercussions. Compared to the baseline period of 2018-2020, a similar upward trend in environmental impacts is observed, showing an average annual growth rate of 5.88 % (ranging from 0.45 to 18.56 %) under the sustainable pathway (SSP119) scenario; 5.90 % (ranging from 1.00 to 18.15 %) for the intermediate development pathway (SSP245); and 6.22 % (ranging from 1.16 to 17.74 %) under the rapid economic development pathway (SSP585). Variation in rainfall is identified as the primary driving factor of the increased environmental impacts, whereas its relationship with rising temperatures is not significant. The results suggest adopting farming practices as a vital strategy for smallholder farms to mitigate climate change impacts. Emphasizing appropriate fertilizer application and straw recycling can significantly reduce the environmental footprint of wheat production. Standardized fertilization could reduce the environmental impact index by 11.10 to 47.83 %, while straw recycling might decrease respiratory inorganics and photochemical oxidant formation potential by over 40 %. Combined, these approaches could lower the impact index by 12.31 to 63.38 %. The findings highlight the importance of adopting enhanced farming practices within smallholder farming systems in the context of climate change. Spotlights: center dot China's smallholder wheat farming is increasingly exposed to climate threats, risking resource depletion and pollution center dot Increasing eco-impacts of smallholder wheat farming could be mitigated by regulated fertilizer use and straw recycling center dot Life cycle assessment combined with machine learning targets future environmental impacts in dynamic climate scenarios center dot The study offers actionable policy advice for sustainable smallholder wheat farming practices center dot Future work may probe machine learning's role in forecasting smallholder production behaviors and farming decision aid
英文关键词	Smallholder; Policy making; Climate change; Farming practice; Machine learning; Life cycle assessment; Wheat
语种	英语
WOS研究方向	Environmental Sciences & Ecology
WOS类目	Environmental Sciences
WOS记录号	WOS:001221561600001
来源期刊	SCIENCE OF THE TOTAL ENVIRONMENT
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/308705
作者单位	Lanzhou University; Lanzhou University
推荐引用方式 GB/T 7714	Yu, Chunxiao,Xu, Gang,Cai, Ming,et al. Predicting environmental impacts of smallholder wheat production by coupling life cycle assessment and machine learning[J],2024,921.
APA	Yu, Chunxiao.,Xu, Gang.,Cai, Ming.,Li, Yuan.,Wang, Lijia.,...&Lin, Huilong.(2024).Predicting environmental impacts of smallholder wheat production by coupling life cycle assessment and machine learning.SCIENCE OF THE TOTAL ENVIRONMENT,921.
MLA	Yu, Chunxiao,et al."Predicting environmental impacts of smallholder wheat production by coupling life cycle assessment and machine learning".SCIENCE OF THE TOTAL ENVIRONMENT 921(2024).