• 首 页
  • 实验室简介
  • 科学研究
    • 实验室定位
    • 研究目标
    • 研究方向
    • 研究项目
    • 研究工作进展
  • 科研队伍
    • 队伍建设
    • 学科组
  • 研究生教育
    • 简介
    • 学科与学位点
    • 研究生导师
    • 在读研究生
    • 毕业研究生
  • 科研成果
    • 获奖
    • 专著
    • 学术论文
    • 专利
  • 联系我们
  • 首页
  • 实验室简介
  • 科学研究
    • 实验室定位
    • 研究目标
    • 研究方向
    • 研究项目
    • 研究工作进展
  • 科研队伍
    • 队伍建设
    • 学科组
  • 研究生教育
    • 简介
    • 学科与学位点
    • 研究生导师
    • 在读研究生
    • 毕业研究生
  • 科研成果
    • 获奖
    • 专著
    • 学术论文
    • 专利
  • 联系我们
  1. 当前位置:首页    新闻动态    最新成果
最新成果

Comparative Analysis of Two Machine Learning Algorithms in Predicting Site-Level Net Ecosystem Exchange in Major Biomes

来源:

来源:   |  发布时间:2021-07-16   |  【 大  中  小 】

论文题目:

Comparative Analysis of Two Machine Learning Algorithms in Predicting Site-Level Net Ecosystem Exchange in Major Biomes

英文论文题目:

Comparative Analysis of Two Machine Learning Algorithms in Predicting Site-Level Net Ecosystem Exchange in Major Biomes

第一作者:

Liu, Jianzhao

英文第一作者:

Liu, Jianzhao

联系作者:

Yuan, Fenghui(非本单位)

英文联系作者:

Yuan, Fenghui(非本单位)

外单位作者单位:

 

英文外单位作者单位:

 

发表年度:

2021

卷:

13

期:

12

页码:

 

摘要:

The net ecosystem CO2 exchange (NEE) is a critical parameter for quantifying terrestrial ecosystems and their contributions to the ongoing climate change. The accumulation of ecological data is calling for more advanced quantitative approaches for assisting NEE prediction. In this study, we applied two widely used machine learning algorithms, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), to build models for simulating NEE in major biomes based on the FLUXNET dataset. Both models accurately predicted NEE in all biomes, while XGBoost had higher computational efficiency (6 similar to 62 times faster than RF). Among environmental variables, net solar radiation, soil water content, and soil temperature are the most important variables, while precipitation and wind speed are less important variables in simulating temporal variations of site-level NEE as shown by both models. Both models perform consistently well for extreme climate conditions. Extreme heat and dryness led to much worse model performance in grassland (extreme heat: R-2 = 0.66 similar to 0.71, normal: R-2 = 0.78 similar to 0.81; extreme dryness: R-2 = 0.14 similar to 0.30, normal: R-2 = 0.54 similar to 0.55), but the impact on forest is less (extreme heat: R-2 = 0.50 similar to 0.78, normal: R-2 = 0.59 similar to 0.87; extreme dryness: R-2 = 0.86 similar to 0.90, normal: R-2 = 0.81 similar to 0.85). Extreme wet condition did not change model performance in forest ecosystems (with R-2 changing -0.03 similar to 0.03 compared with normal) but led to substantial reduction in model performance in cropland (with R-2 decreasing 0.20 similar to 0.27 compared with normal). Extreme cold condition did not lead to much changes in model performance in forest and woody savannas (with R-2 decreasing 0.01 similar to 0.08 and 0.09 compared with normal, respectively). Our study showed that both models need training samples at daily timesteps of >2.5 years to reach a good model performance and >5.4 years of daily samples to reach an optimal model performance. In summary, both RF and XGBoost are applicable machine learning algorithms for predicting ecosystem NEE, and XGBoost algorithm is more feasible than RF in terms of accuracy and efficiency.

英文摘要:

The net ecosystem CO2 exchange (NEE) is a critical parameter for quantifying terrestrial ecosystems and their contributions to the ongoing climate change. The accumulation of ecological data is calling for more advanced quantitative approaches for assisting NEE prediction. In this study, we applied two widely used machine learning algorithms, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), to build models for simulating NEE in major biomes based on the FLUXNET dataset. Both models accurately predicted NEE in all biomes, while XGBoost had higher computational efficiency (6 similar to 62 times faster than RF). Among environmental variables, net solar radiation, soil water content, and soil temperature are the most important variables, while precipitation and wind speed are less important variables in simulating temporal variations of site-level NEE as shown by both models. Both models perform consistently well for extreme climate conditions. Extreme heat and dryness led to much worse model performance in grassland (extreme heat: R-2 = 0.66 similar to 0.71, normal: R-2 = 0.78 similar to 0.81; extreme dryness: R-2 = 0.14 similar to 0.30, normal: R-2 = 0.54 similar to 0.55), but the impact on forest is less (extreme heat: R-2 = 0.50 similar to 0.78, normal: R-2 = 0.59 similar to 0.87; extreme dryness: R-2 = 0.86 similar to 0.90, normal: R-2 = 0.81 similar to 0.85). Extreme wet condition did not change model performance in forest ecosystems (with R-2 changing -0.03 similar to 0.03 compared with normal) but led to substantial reduction in model performance in cropland (with R-2 decreasing 0.20 similar to 0.27 compared with normal). Extreme cold condition did not lead to much changes in model performance in forest and woody savannas (with R-2 decreasing 0.01 similar to 0.08 and 0.09 compared with normal, respectively). Our study showed that both models need training samples at daily timesteps of >2.5 years to reach a good model performance and >5.4 years of daily samples to reach an optimal model performance. In summary, both RF and XGBoost are applicable machine learning algorithms for predicting ecosystem NEE, and XGBoost algorithm is more feasible than RF in terms of accuracy and efficiency.

刊物名称:

Remote Sensing

英文刊物名称:

Remote Sensing

论文全文:

 

英文论文全文:

 

全文链接:

 

其它备注:

 

英文其它备注:

 

学科:

 

英文学科:

 

影响因子:

 

第一作者所在部门:

 

英文第一作者所在部门:

 

论文出处:

 

英文论文出处:

 

论文类别:

 

英文论文类别:

 

参与作者:

J. Z. Liu, Y. J. Zuo, N. N. Wang, F. H. Yuan, X. H. Zhu, L. H. Zhang, J. W. Zhang, Y. Sun, Z. Y. Guo, Y. D. Guo, X. Song, C. C. Song and X. F. Xu

英文参与作者:

J. Z. Liu, Y. J. Zuo, N. N. Wang, F. H. Yuan, X. H. Zhu, L. H. Zhang, J. W. Zhang, Y. Sun, Z. Y. Guo, Y. D. Guo, X. Song, C. C. Song and X. F. Xu


附件下载:

版权所有 © 中国科学院长春净月潭遥感实验站 吉ICP备05002032号-1 吉公网安备22017302000214号
地址:吉林省长春市高新北区盛北大街4888号 邮编:130102
电话:+86 431 85542227  Email:jyrs@iga.ac.cn