Data and code associated with: <strong>Satellite-driven evaluation of ecological environmental quality based on the PSR framework</strong>
收藏资源简介：
These are data files and code associated with, Satellite-driven evaluation of ecological environmental quality based on the PSR framework <br> <strong> Abstract：</strong> <br> Ever-increasing human activities have resulted in significant environmental degradation. It is crucial for environmental protection to monitor and evaluate the ecological environmental quality (EEQ) in a timely and accurate manner. Remote sensing technology has been widely used to quantify EEQ. However, current remote sensing EEQ evaluation methods suffer from deficiencies with regard to the indicator system and the EEQ quantification, reducing the accuracy of EEQ evaluations. Therefore, this study proposes a novel method to evaluate EEQ. Remote-sensing indicators used in the pressure-state-response (PSR) framework are selected based on the traditional EEQ evaluation system, and deep neural networks (DNNs) are used to quantify EEQ. A case study is conducted in Guangdong and Guangzhou city, China, to validate the method. The trends in EEQ from 2013 to 2019 are analyzed using the Sen and Mann-Kendall (MK) tests in Guangzhou city. The results show the following. (1) The proposed method has a significantly higher EEQ estimation accuracy (determination coefficient (R2) of 0.75 and normalized root mean square error (NRMSE) of 13.61%) than the commonly used remote sensing ecological index (RSEI) method (R2 of 0.51 and NRMSE of 19.13%). (2) The five remote sensing indicators (RSI) in the PSR framework are highly correlated with EEQ, with a minimum |r| = 0.52. (3) In Guangzhou, the EEQ increased from southwest to northeast and showed an increasing trend from 2013 to 2019, consistent with actual conditions. This study provides a new strategy for the high-accuracy estimation of EEQ based on remote sensing data. <br> <strong>File list:</strong> EEQ measurements by district and county in Guangdong Province( EEQ measurements.zip ) PM2.5 concentration data ( PM2.5_ECHAP_PM2.5_Y1K_2018_V3_flip.zip ) Land cover data ( CLCD_v01_2016_albert_guangdong.zip ) ASTER GDEM ( DEM.zip ) GPM_3IMERGM L3 1-month V06 ( GPM monthly precipitation data downloading(GEE code).txt ) Landsat 8 OLI/TIRS ( NDVI LSM and EVI downloading（GEE code）.txt ) <br> Data from the Google Earth Enging (GEE) platform were provided in the form of code. Soil type data was provided by the local land reclamation centre under a confidentiality agreement. In respect of this agreement, we are unable to make this data publicly available. Further more, soil type data is confidential data relating to the project and therefore not publicly available.
本数据集包含与基于压力-状态-响应（Pressure-State-Response，简称PSR）框架的卫星驱动生态环境质量评估研究相关的数据文件与代码。 摘要： 日益频繁的人类活动已造成严重的环境退化。及时、精准地监测与评估生态环境质量（Ecological Environmental Quality，简称EEQ）对于环境保护工作而言至关重要。遥感技术已被广泛应用于生态环境质量的量化评估中，但当前的遥感生态环境质量评估方法在指标体系与生态环境质量量化环节均存在不足，导致评估精度受限。为此，本研究提出了一种全新的生态环境质量评估方法：基于传统生态环境质量评估体系，选取适配压力-状态-响应框架的遥感指标，并采用深度神经网络（Deep Neural Networks，DNNs）实现生态环境质量的量化。本研究以中国广东省及广州市为研究区域开展案例研究以验证该方法，并利用森斜率检验与曼-肯德尔（Mann-Kendall，简称MK）检验分析了2013-2019年广州市的生态环境质量变化趋势。研究结果如下：（1）相较于常用的遥感生态指数（Remote Sensing Ecological Index，RSEI）方法（决定系数R²为0.51，归一化均方根误差NRMSE为19.13%），本研究提出的方法生态环境质量估算精度显著更高，其决定系数R²达0.75，归一化均方根误差NRMSE仅为13.61%。（2）压力-状态-响应框架下的5项遥感指标（Remote Sensing Indicators，RSI）与生态环境质量均呈现高度相关性，相关系数的最小绝对值|r|为0.52。（3）广州市生态环境质量整体呈现西南低、东北高的分布格局，且2013-2019年整体呈上升趋势，与实际情况相符。本研究为基于遥感数据的生态环境质量高精度估算提供了全新的研究思路。 数据集文件列表： 广东省各区县生态环境质量实测数据（EEQ measurements.zip）、PM2.5浓度数据（PM2.5_ECHAP_PM2.5_Y1K_2018_V3_flip.zip）、土地覆盖数据（CLCD_v01_2016_albert_guangdong.zip）、ASTER数字高程模型（ASTER GDEM，DEM.zip）、GPM 3IMERGM L3 1个月V06数据集（GPM月度降水数据下载代码（GEE代码）.txt）、Landsat 8 OLI/TIRS影像相关数据（NDVI、LSM及EVI下载代码（GEE代码）.txt） 谷歌地球引擎（Google Earth Engine，GEE）平台的相关数据以代码形式提供。土壤类型数据由当地土地复垦中心根据保密协议提供，依据该协议，我们无法公开此类数据。此外，土壤类型数据属于本项目的机密数据，因此不予公开。
