• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

用于评估十亿棵树造林项目生态影响的机器学习与时空分析

Machine Learning and Spatio Temporal Analysis for Assessing Ecological Impacts of the Billion Tree Afforestation Project.

作者信息

Mehmood Kaleem, Anees Shoaib Ahmad, Muhammad Sultan, Shahzad Fahad, Liu Qijing, Khan Waseem Razzaq, Shrahili Mansour, Ansari Mohammad Javed, Dube Timothy

机构信息

College of Forestry Beijing Forestry University Beijing China.

Key Laboratory for Silviculture and Conservation of Ministry of Education Beijing Forestry University Beijing China.

出版信息

Ecol Evol. 2025 Feb 19;15(2):e70736. doi: 10.1002/ece3.70736. eCollection 2025 Feb.

DOI:10.1002/ece3.70736
PMID:39975709
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11839268/
Abstract

This study evaluates the Billion Tree Afforestation Project (BTAP) in Pakistan's Khyber Pakhtunkhwa (KPK) province using remote sensing and machine learning. Applying Random Forest (RF) classification to Sentinel-2 imagery, we observed an increase in tree cover from 25.02% in 2015 to 29.99% in 2023 and a decrease in barren land from 20.64% to 16.81%, with an accuracy above 85%. Hotspot and spatial clustering analyses revealed significant vegetation recovery, with high-confidence hotspots rising from 36.76% to 42.56%. A predictive model for the Normalized Difference Vegetation Index (NDVI), supported by SHAP analysis, identified soil moisture and precipitation as primary drivers of vegetation growth, with the ANN model achieving an of 0.8556 and an RMSE of 0.0607 on the testing dataset. These results demonstrate the effectiveness of integrating machine learning with remote sensing as a framework to support data-driven afforestation efforts and inform sustainable environmental management practices.

摘要

本研究利用遥感和机器学习对巴基斯坦开伯尔-普赫图赫瓦省（KPK）的十亿棵树造林项目（BTAP）进行了评估。通过对哨兵-2影像应用随机森林（RF）分类，我们观察到树木覆盖面积从2015年的25.02%增加到2023年的29.99%，荒地面积从20.64%减少到16.81%，准确率超过85%。热点和空间聚类分析显示植被有显著恢复，高置信度热点从36.76%增至42.56%。在SHAP分析的支持下，归一化植被指数（NDVI）的预测模型确定土壤湿度和降水是植被生长的主要驱动因素，人工神经网络（ANN）模型在测试数据集上的R²为0.8556，均方根误差（RMSE）为0.0607。这些结果证明了将机器学习与遥感相结合作为支持数据驱动的造林工作及为可持续环境管理实践提供信息的框架的有效性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/a4710d259373/ECE3-15-e70736-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/ace384c099d8/ECE3-15-e70736-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/c7ca2b3ae8f4/ECE3-15-e70736-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/b915474402d7/ECE3-15-e70736-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/8878e6530d91/ECE3-15-e70736-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/99746cf72859/ECE3-15-e70736-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/251a4f63ecec/ECE3-15-e70736-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/c171ba11bf55/ECE3-15-e70736-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/499359425ce9/ECE3-15-e70736-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/302af8ae2eff/ECE3-15-e70736-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/ffe176d238b6/ECE3-15-e70736-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/1918c3b46b25/ECE3-15-e70736-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/5c0c4264adf0/ECE3-15-e70736-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/a4710d259373/ECE3-15-e70736-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/ace384c099d8/ECE3-15-e70736-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/c7ca2b3ae8f4/ECE3-15-e70736-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/b915474402d7/ECE3-15-e70736-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/8878e6530d91/ECE3-15-e70736-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/99746cf72859/ECE3-15-e70736-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/251a4f63ecec/ECE3-15-e70736-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/c171ba11bf55/ECE3-15-e70736-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/499359425ce9/ECE3-15-e70736-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/302af8ae2eff/ECE3-15-e70736-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/ffe176d238b6/ECE3-15-e70736-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/1918c3b46b25/ECE3-15-e70736-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/5c0c4264adf0/ECE3-15-e70736-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/85e0/11839268/a4710d259373/ECE3-15-e70736-g005.jpg

相似文献

1
Machine Learning and Spatio Temporal Analysis for Assessing Ecological Impacts of the Billion Tree Afforestation Project.用于评估十亿棵树造林项目生态影响的机器学习与时空分析
Ecol Evol. 2025 Feb 19;15(2):e70736. doi: 10.1002/ece3.70736. eCollection 2025 Feb.
2
Modeling climate change impacts and predicting future vulnerability in the Mount Kenya forest ecosystem using remote sensing and machine learning.利用遥感和机器学习对肯尼亚山森林生态系统的气候变化影响进行建模并预测未来脆弱性。
Environ Monit Assess. 2025 May 6;197(6):631. doi: 10.1007/s10661-025-14089-0.
3
Spatio-temporal classification of land use and land cover and its changes in Kerala using remote sensing and machine learning approach.利用遥感和机器学习方法对喀拉拉邦的土地利用/土地覆盖进行时空分类及其变化研究。
Environ Monit Assess. 2024 Apr 18;196(5):459. doi: 10.1007/s10661-024-12633-y.
4
Enhancing vegetation cover growth through water spreading bunds and dry afforestation in arid rangelands: Integrating remote sensing indicators with field insights.通过在干旱牧场设置集水埂和进行旱作造林来促进植被覆盖生长：将遥感指标与实地观察相结合。
Sci Total Environ. 2025 May 25;978:179382. doi: 10.1016/j.scitotenv.2025.179382. Epub 2025 Apr 19.
5
Modelling, mapping and monitoring of forest cover changes, using support vector machine, kernel logistic regression and naive bayes tree models with optical remote sensing data.利用支持向量机、核逻辑回归和朴素贝叶斯树模型以及光学遥感数据对森林覆盖变化进行建模、制图和监测。
Heliyon. 2023 Jan 26;9(2):e13212. doi: 10.1016/j.heliyon.2023.e13212. eCollection 2023 Feb.
6
Role of local communities in forest landscape restoration: Key lessons from the Billion Trees Afforestation Project, Pakistan.地方社区在森林景观恢复中的作用：巴基斯坦十亿树木造林项目的主要经验教训。
Sci Total Environ. 2021 Jun 10;772:145613. doi: 10.1016/j.scitotenv.2021.145613. Epub 2021 Feb 4.
7
Irrigated Crop Types Mapping in Tashkent Province of Uzbekistan with Remote Sensing-Based Classification Methods.利用基于遥感的分类方法对乌兹别克斯坦塔什干省的灌溉作物类型进行制图。
Sensors (Basel). 2022 Jul 29;22(15):5683. doi: 10.3390/s22155683.
8
Improvement of spatial estimation for soil organic carbon stocks in Yuksekova plain using Sentinel 2 imagery and gradient descent-boosted regression tree.利用 Sentinel 2 图像和梯度提升回归树提高于约克塞瓦平原土壤有机碳储量的空间估算精度。
Environ Sci Pollut Res Int. 2023 Apr;30(18):53253-53274. doi: 10.1007/s11356-023-26064-8. Epub 2023 Feb 28.
9
Machine learning models for predicting vegetation conditions in Mahanadi River basin.用于预测马哈德维河流域植被状况的机器学习模型。
Environ Monit Assess. 2023 Nov 2;195(12):1401. doi: 10.1007/s10661-023-12006-x.
10
Spatio-temporal change detection of land use and land cover in Malakand Division Khyber Pakhtunkhwa, Pakistan, using remote sensing and geographic information system.利用遥感和地理信息系统对巴基斯坦开伯尔-普赫图赫瓦省马拉坎德专区土地利用和土地覆盖的时空变化检测
Environ Sci Pollut Res Int. 2023 Jan;30(4):10982-10994. doi: 10.1007/s11356-022-22960-7. Epub 2022 Sep 10.

引用本文的文献

1
Exploring vegetation health in Southern Thailand under climate stress from temperature and water impacts between 2000 and 2023.探索2000年至2023年期间，受温度和水分影响的气候压力下泰国南部的植被健康状况。
Sci Rep. 2025 Aug 20;15(1):30491. doi: 10.1038/s41598-025-16293-x.
2
Mechanism of arable land ecological security impact on arable land quality in different geomorphological areas of Northeast China.中国东北不同地貌区耕地生态安全对耕地质量的影响机制
Sci Rep. 2025 Jul 1;15(1):21730. doi: 10.1038/s41598-025-03447-0.

本文引用的文献

1
Global patterns and controlling factors of tree bark C : N : P stoichiometry in forest ecosystems consistent with biogeochemical niche hypothesis.森林生态系统中树皮碳：氮：磷化学计量比的全球模式及控制因素，与生物地球化学生态位假说一致。
New Phytol. 2024 Nov;244(4):1303-1314. doi: 10.1111/nph.20119. Epub 2024 Sep 15.
2
Assessing forest fragmentation due to land use changes from 1992 to 2023: A spatio-temporal analysis using remote sensing data.评估1992年至2023年土地利用变化导致的森林破碎化：基于遥感数据的时空分析
Heliyon. 2024 Jul 16;10(14):e34710. doi: 10.1016/j.heliyon.2024.e34710. eCollection 2024 Jul 30.
3
Analyzing vegetation health dynamics across seasons and regions through NDVI and climatic variables.
通过 NDVI 和气候变量分析跨季节和区域的植被健康动态。
Sci Rep. 2024 May 23;14(1):11775. doi: 10.1038/s41598-024-62464-7.
4
shaPRS: Leveraging shared genetic effects across traits or ancestries improves accuracy of polygenic scores.shaPRS：利用跨性状或祖源的共享遗传效应可提高多基因评分的准确性。
Am J Hum Genet. 2024 Jun 6;111(6):1006-1017. doi: 10.1016/j.ajhg.2024.04.009. Epub 2024 May 3.
5
Spatial autocorrelation equation based on Moran's index.基于莫兰指数的空间自相关方程。
Sci Rep. 2023 Nov 7;13(1):19296. doi: 10.1038/s41598-023-45947-x.
6
Understanding the spatio-temporal behaviour of the sunflower crop for subfield areas delineation using Sentinel-2 NDVI time-series images in an organic farming system.利用哨兵-2归一化植被指数（NDVI）时间序列图像理解有机农业系统中用于子区域划分的向日葵作物的时空行为。
Heliyon. 2023 Aug 30;9(9):e19507. doi: 10.1016/j.heliyon.2023.e19507. eCollection 2023 Sep.
7
Do adaptive policy adjustments deliver ecosystem-agriculture-economy co-benefits in land degradation neutrality efforts? Evidence from southeast coast of China.适应性政策调整能否在土地退化中性化努力中实现生态系统-农业-经济的协同效益？来自中国东南沿海的证据。
Environ Monit Assess. 2023 Sep 15;195(10):1215. doi: 10.1007/s10661-023-11821-6.
8
A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging.医学成像中人工智能的交叉验证指南
Radiol Artif Intell. 2023 May 24;5(4):e220232. doi: 10.1148/ryai.220232. eCollection 2023 Jul.
9
A Hypothesis Test for Detecting Distance-Specific Clustering and Dispersion in Areal Data.一种用于检测区域数据中距离特定聚类和离散度的假设检验。
Spat Stat. 2023 Jun;55. doi: 10.1016/j.spasta.2023.100757. Epub 2023 May 19.
10
A multi-layer perceptron-Markov chain based LULC change analysis and prediction using remote sensing data in Prayagraj district, India.基于多层感知器-马尔可夫链的印度普拉亚格拉杰地区土地利用/土地覆盖变化分析与预测：利用遥感数据
Environ Monit Assess. 2023 Apr 27;195(5):619. doi: 10.1007/s10661-023-11205-w.