地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (6): 1040-1049.doi: 10.12082/dqxxkx.2021.200474

• 地理空间分析综合应用 • 上一篇    下一篇

随机森林算法在全球干旱评估中的应用

方秀琴1,2,*(), 郭晓萌1, 袁玲1, 杨露露1, 任立良1, 朱求安1,2   

  1. 1.河海大学水文水资源学院,南京 211100
    2.河海大学海岸灾害及防护教育部重点实验室,南京 210024
  • 收稿日期:2020-08-19 修回日期:2020-12-23 出版日期:2021-06-25 发布日期:2021-08-25
  • 通讯作者: 方秀琴
  • 作者简介:方秀琴(1978— ),女,安徽池州人,博士,副教授,主要从事地表参数遥感反演、水文模型集成及水旱灾害防治等研究。E-mail: kinkinfang@hhu.edu.cn
  • 基金资助:
    国家重点研发计划项目(2016YFA0601500);国家自然科学基金项目(42071040);中央高校基本科研业务费专项(2019B04714)

Application of Random Forest Algorithm in Global Drought Assessment

FANG Xiuqin1,2,*(), GUO Xiaomeng1, YUAN Ling1, YANG Lulu1, REN Liliang1, ZHU Qiuan1,2   

  1. 1. College of Hydrology and Water Resources, Hohai University, Nanjing 211100, China
    2. Key Laboratory of Ministry of Education for Coastal Disaster and Protection, Hohai University, Nanjing 210024, China
  • Received:2020-08-19 Revised:2020-12-23 Online:2021-06-25 Published:2021-08-25
  • Contact: FANG Xiuqin
  • Supported by:
    National Key Research and Development Program of China(2016YFA0601500);National Natural Science Foundation of China(42071040);Fundamental Research Funds for the Central Universities(2019B04714)

摘要:

干旱是发生频率最高,造成社会、经济损失和生态破坏最严重、最广泛的自然灾害之一,因此对干旱进行可靠、有效的评估十分重要。本文以月平均降水、月平均温度、月最高温度、月最低温度、土壤湿度、蒸散发、NDVI、叶绿素荧光等作为解释变量,以基于SPI的干旱等级作为目标变量,采用随机森林算法,以2007—2012年的数据作为训练数据,以2013—2014年的数据作为预测数据,对全球11个气候区分别建立干旱等级评估模型。研究结论如下:SPI的时间尺度影响模型精度,在基于SPI1、SPI3、SPI6和SPI12划分的干旱等级的评估模型中,以基于SPI1的干旱等级为目标变量的模型的预测精度(60%~75%)较高,且模型能够捕捉到EM-DAT旱灾记录次数的90.91%、月份的78.47%,表明该模型对实际干旱事件具有良好的评估性能;干旱等级划分标准对模型的预测性能影响较小,可根据需求选择标准I(干旱/非干旱)或标准Ⅱ(重旱/非重旱)进行干旱评估;解释变量的相对重要性与SPI的时间尺度和气候差异等因素有关。降水对基于SPI1的干旱等级的重要性最大,随着SPI时间尺度的增加,降水的重要性逐渐减小,温度、土壤湿度、NDVI和ET的重要性逐渐增大。降水以外的其他变量在不同气候区的重要性不同。在热带气候区、亚寒带气候区和苔原气候区,温度或蒸散发的影响较大;在干燥气候区,土壤湿度的影响较大;在温带气候区,仍以降水的相对重要性最大;在湿润大陆性气候区,植被对干旱的影响较大。

关键词: 干旱评估, 干旱等级, SPI, 随机森林, 气候分区, 降水, 气温, 土壤湿度

Abstract:

Drought is one of the most frequent and widespread climate extremes, causing devasting social, economic and ecological damages. It is of key importance to evaluate drought reliably and effectively. In this study, in order to assess global drought grade, the Random Forest (RF) algorithm was used to establish the drought grade assessment models for the 11 climate zones in the world. We chose monthly mean precipitation, mean temperature, maximum temperature, minimum temperature, soil moisture, evapotranspiration (ET), Normalized Difference Vegetation Index (NDVI), and Sun/Solar-induced Chlorophyll Fluorescence (SIF) as explanatory variables and drought grades based on Standardized Precipitation Index (SPI) as target variable. The SPI on different timescales of 1 month, 3 months, 6 months and 12 months were labeled as SPI1, SPI3, SPI6 and SPI12, respectively. The data from 2007 to 2012 were used as training data of the assessment models while those from 2013 to 2014 were used as prediction data. The results showed that: (1) The temporal scale of SPI influenced the model accuracy. Among the models with drought grade based on SPI1、SPI3、SPI6 and SPI12, the one with drought grade based on SPI1 had the highest accuracy (60%~75%) and prediction performance. The model with drought grade based on SPI1 was able to capture 90.91% of the drought records in the global emergency events database (EM-DAT). It could capture 78.47% of the drought duration month in the EM-DAT. The agreements with records and drought duration month in the EM-DAT indicated the good performance of the drought grade assessment model based on 1-month SPI and RF algorithm. (2) The drought grading criterion had little impact on the model performance. Users could select criterion I (drought/not drought) or criterion II (severe/not severe) depending on the real needs. (3) The relative importance of each explanatory variable depended on both the temporal scale of SPI and climatic differences. Precipitation was the most important factor for the drought grade based on SPI1. The importance of precipitation decreased and the ones of other explanatory variables such as temperature, soil moisture, NDVI, and ET increased as the timescale of SPI increased. The importance of variables except precipitation showed differences in different climate zones. Among the tropical, subfrigid, and tundra climate zones, temperature or ET is relatively important for drought. Soil moisture is relatively important in dry climate zone and precipitation is the most important in mild temperate climate zone, while vegetation is relatively important in the humid continental climate zone.

Key words: drought evaluation, drought grade, SPI, random forest, climate zone, precipitation, temperature, soil moisture