Pulse Brain · Growing Health Evidence Index
Tier 3 — Observational / field trialPeer-reviewed

Decrypting spatiotemporal evolution and influencing factors of cultivated land use carbon compensation in the middle reaches of Yangtze River: An interpretable machine learning approach

Tiangui Lv, Menghan Yuan, Qiao Zhao, Xianzhe Huang, Shufei Fu, Wang Li

Journal for Nature Conservation · 2026

Read source ↗ All evidence

Summary

This study applies interpretable machine learning to map and explain spatiotemporal variation in carbon compensation across cultivated lands in China's middle Yangtze River region. The authors appear to have identified key environmental, climatic, and land-use drivers of carbon dynamics in this agricultural landscape, potentially offering insights for regional carbon accounting and land-use policy. The use of explainable machine learning methods suggests an attempt to make complex carbon cycle patterns more transparent for decision-making.

UK applicability

The specific carbon compensation mechanisms and drivers identified may have limited direct applicability to UK arable systems given different climate, soil types, and agricultural practices. However, the methodological approach of using interpretable machine learning for spatiotemporal carbon assessment could inform UK soil carbon monitoring and natural capital accounting frameworks.

Key measures

Cultivated land carbon compensation values; spatiotemporal distribution patterns; machine learning feature importance for influencing factors

Outcomes reported

The study examined spatiotemporal patterns and driving factors of carbon compensation in cultivated land across the middle Yangtze River basin using interpretable machine learning methods. Carbon compensation metrics and their evolution over time were modelled to identify key influencing factors at landscape scale.

Theme
Climate & resilience
Subject
Climate & greenhouse gas mitigation
Study type
Research
Study design
Observational spatial analysis with machine learning
Source type
Peer-reviewed study
Status
Published
Geography
China
System type
Arable cereals
DOI
10.1016/j.jnc.2026.127295
Catalogue ID
SNmohi6m4x-v3h7aq

Topic tags

Pulse AI · ask about this record

Dig deeper with Pulse AI.

Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.