地球信息科学学报 ›› 2020, Vol. 22 ›› Issue (8): 1666-1678.doi: 10.12082/dqxxkx.2020.190142

• 遥感科学与应用技术 • 上一篇    下一篇

基于随机森林算法的地表温度鲁棒降尺度方法

李婉1(), 牛陆2,3, 陈虹4,*(), 吴骅2,3   

  1. 1.中国科学院空天信息创新研究院 中国科学院定量遥感信息技术重点实验室,北京 100094
    2.中国科学院地理科学与资源研究所 资源与环境信息系统国家重点实验室,北京 100101
    3.中国科学院大学资源与环境学院,北京 100049
    4.中国自然资源航空物探遥感中心,北京 100083
  • 收稿日期:2019-04-01 修回日期:2019-12-12 出版日期:2020-08-25 发布日期:2020-10-25
  • 通讯作者: 陈虹 E-mail:liwan@aircas.ac.cn;chch1223@126.com
  • 作者简介:李 婉(1994— ),女,山东济宁人,硕士生,主要从事热红外遥感、尺度转换方面的研究。E-mail:liwan@aircas.ac.cn
  • 基金资助:
    国家自然科学基金项目(41901308);国家自然科学基金项目(41601395);国家自然科学基金项目(61601440);国家重点研发计划资助(2018YFB0504800);国家重点研发计划资助(2018YFB 0504805);中科院大科学项目“全球遥感定标基准网”(181811KYSB20160040);定量遥感信息外场计量技术创新交叉团队(Y70305A1CY)

Robust Downscaling Method of Land Surface Temperature by Using Random Forest Algorithm

LI Wan1(), NIU Lu2,3, CHEN Hong4,*(), WU Hua2,3   

  1. 1. Key Laboratory of Quantitative Remote Sensing Information Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
    2. State Key Laboratory of Resources and Environment Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
    3. University of Chinese Academy of Sciences, Beijing 100049, China
    4. China Aero Geophysical Survey & Remote Sensing Center for Nature Resources, Beijing 100083, China
  • Received:2019-04-01 Revised:2019-12-12 Online:2020-08-25 Published:2020-10-25
  • Contact: CHEN Hong E-mail:liwan@aircas.ac.cn;chch1223@126.com
  • Supported by:
    National Natural Science Foundation of China(41901308);National Natural Science Foundation of China(41601395);National Natural Science Foundation of China(61601440);National Key Research and Development Program of China(2018YFB0504800);National Key Research and Development Program of China(2018YFB 0504805);Bureau of International Co-operation Chinese Academy of Sciences(181811KYSB20160040);Quantitative Remote Sensing Innovation Cross Team(Y70305A1CY)

摘要:

陆地表面温度是描述区域或者全球范围内陆地表面与大气的相互作用和能量平衡最重要的环境参数之一。针对目前尚未有遥感卫星能够同时提供具有高时间和高空间分辨率的地表温度产品的问题,国内外学者发展了多种对低空间分辨率的地表温度进行降尺度的算法。然而,由于对地表温度解释变量和降尺度模型的选择往往具有区域局限性,导致了降尺度模型的泛化能力受到了一定的限制。本文首先评估了地表反射率、遥感光谱指数、地形因子、地表覆盖、经纬度以及基本状态变量6类环境参量与地表温度之间的相关关系,并在此基础上筛选出最佳解释变量;同时,结合在非线性回归问题上表现比较优秀的随机森林算法,建立了一种鲁棒性的基于随机森林算法地表温度降尺度模型(RRF)。本文选取了中国范围内具有代表性的11个地区作为主要研究区,将空间分辨率为1 km的MODIS地表温度产品降尺度至90 m。以北京市2个典型地表类型的子区域为代表研究区,通过与传统的基于归一化植被指数与地表温度相关关系的TsHARP模型,以及基于红波段和近红外波段以及地表高程作为尺度因子建立的简单Basic-RF模型的对比分析可得,RRF模型在2个子研究区降尺度结果均优于TsHARP模型和Basic-RF模型,其均方根误差分别为2.39 K和2.27 K。通过进一步对2个子研究区训练的RRF进行交叉验证,证明在一个研究区训练的RRF应用至另一研究区的降尺度时,RRF模型表现出了较好的鲁棒性,降尺度结果的均方根误差分别为2.56 K和2.44 K,精度误差相差仅为0.17 K。通过将RRF应用于中国范围内的多个研究区,结果表明利用少量训练数据构建的RRF模型适用于大范围的区域,地表温度降尺度结果都能取得较好的精度。

关键词: 地表温度, 热红外遥感, 降尺度, 机器学习, 随机森林, 解释变量, MODIS, 鲁棒性

Abstract:

Land Surface Temperature (LST) is one of the most important environmental parameters that describe the atmospheric and land surface interactions and energy balance in the terrestrial ecosystem at regional and global scales. Due to the trade off between high temporal and high spatial resolutions of remotely sensed LST products, many downscaling algorithms have been developed. However, the selection of explanatory variables of LST and downscaling models are often restricted by study location, which limits the generalization performance of these models. In this paper, a robust downscaling method of land surface temperature using Random Forest algorithm (RRF) is proposed after the evaluation of relationships between six variables, including surface reflectance, spectral indices, terrain factors, land cover types, longitude and latitude information, andatmospheric reanalysis data, to establish a nonlinear relationship between LSTs and other land surface parameters. This paper selects 11 regions of China as study areas, the Moderate Resolution Imaging Spectroradiometer (MODIS) LST product is downscaled by RRF from 1 km to 90 m. A comparison with two other downscaling methods (the Basic-RF model and the thermal sharpening (TsHARP) algorithm) is also made. Taking Beijing city as a presentative study area, the RRF model is proved to achieve a more satisfied performance in both study area A and B, in which the RMSEs are 2.39 K and 2.27 K, respectively. Besides, the Root Mean Squared Error (RMSE) of the RRF model trained ins tudy area B and evaluated in study area A is 2.56 K, while the RMSE trained in study area A and evaluated in study area B is 2.44 K, with a small decreasein RMSE (i.e., 0.17 K). Our further experiment results prove the robustness of RRF model trained in a specific region while being applied to other regions, and indicate that we can downscale LST with the RRF model in a large area using a few study areas for model training.

Key words: land surface temperature, thermal infrared remote sensing, downscaling, machine learning, random forest, predictor variable, MODIS, robustness