基于随机森林算法的羌塘草原NDVI时空格局及预测模型
The spatiotemporal pattern and prediction model of NDVI in Qiangtang grassland based on random forest algorithm
李彩琳 1宋彦涛 1张靖 1乌云娜 1孙磊2
作者信息
- 1. 大连民族大学环境与资源学院,辽宁大连 116600
- 2. 西藏农牧学院动物科学学院,西藏林芝 860000
- 折叠
摘要
为揭示羌塘草原2001-2020年植被时空变化格局及其影响因素,并预测气候变化条件下羌塘草原植被可能的变化趋势,本研究基于MODIS NDVI数据以及温度、降水和风速数据,探究了羌塘草原植被覆盖变化与气象因子的关系;利用随机森林、支持向量机和随机梯度下降回归3种机器学习算法建立NDVI预测模型,筛选模拟精度最优模型,进行多情景下植被变化模拟.结果表明:2001-2020年羌塘草原NDVI呈现轻微增加趋势,增长率为0.0003 a-1.NDVI对温度的响应滞后3个月,降水滞后0～1个月,NDVI与风速呈负相关且无滞后.随机森林算法的模拟精度最高(Adjusted R2=0.958).未来植被覆盖度整体提升的情景是增温1.0℃、降水增加25％、风速降低25％.研究结果有助于预警植被退化问题,为气候变化背景下该区域植被生态保护提供科学依据.
Abstract
This study aimed to reveal the spatiotemporal variations and the influencing factors of vegetation in the Qiangtang grassland during 2001-2020,and to predict the change trends of vegetation under climate change sce-narios.Based on the data of MODIS NDVI,temperature,precipitation,and wind speed,we explored the relation-ship between vegetation changes and meteorological factors.Furthermore,NDVI prediction models were establish with three machine learning algorithms of random forest,support vector machine,and random gradient descent re-gression.The optimal model with the best simulation accuracy was selected to simulate vegetation changes under multiple scenarios.We found that NDVI of the Qiangtang grassland showed a slight increasing trend with a growth rate of 0.0003 a-1 from 2001 to 2020.The response of NDVI to temperature lagged by 3 months,precipitation lagged by 0-1 months.NDVI was negatively correlated with wind speed without lag.The random forest algorithm had the highest simulation accuracy(Adjusted R2=0.958).The scenario for improvement of vegetation coverage in the future included 1.0 ℃ increase in temperature,25％increase in precipitation,and 25％decrease in wind speed.This study contributed to early warning of vegetation degradation,which would help vegetation conservation under climate change.
关键词
羌塘草原/归一化植被指数/随机森林/多情景模拟Key words
Qiangtang grassland/normalized difference vegetation index/random forest/multi-scenario prediction引用本文复制引用
基金项目
大连民族大学-西藏农牧学院联合基金(DLMZ-NMXY2021002)
国家民委中青年英才培养计划(2022)()
中央高校基本科研业务费专项(2024)()
出版年
2024
国家科技期刊平台
NSTL
万方数据