迅速准确获取矿区土壤重金属浓度空间分布是污染评价、生态修复、土地整治与复垦的前提与基础。传统土壤重金属浓度调查与测量方法不但昂贵、费时、费力、易产生对环境的二次污染，而且难以满足大范围时空动态监测需求。星载高光谱遥感具有监测范围广、波段连续性强、光谱分辨率高、成本低、效率高等优点，正逐步成为土壤重金属浓度调查的关键技术。因此，利用星载高光谱遥感开展矿区土壤重金属反演具有重要理论与实践价值。

       近年来，高光谱遥感被广泛应用于土壤重金属浓度反演中。然而，目前多数研究局限于在相对稳定的实验室环境下开展离散样点尺度的土壤重金属浓度反演。由于野外环境因素具有不确定性，且土壤光谱信息受到土壤理化性质（如土壤有机质含量、土壤水分等）影响，导致混合像元问题产生，反演精度受到严重影响。因此，利用高光谱遥感影像反演土壤重金属含量仍是学术界一个难点与热点，具有很大挑战性。

       鉴于此，本文以某露天煤矿为研究区，于2020年2月底在研究区实地采集土壤样品110个。在实验室中分别利用ASD地物光谱仪和便携式X射线荧光光谱仪（PXRF）测量了土壤样品反射光谱和土壤锌（Zn）、镍（Ni）和铜（Cu）浓度；并在中国自然资源航空物探遥感中心获取了研究区的高分五号（GF-5）高光谱影像，采用直接校正算法（DS）建立了实验室和GF-5高光谱影像光谱反射率校正模型；利用连续小波变换（CWT）在不同分解尺度上重构了GF-5号高光谱影像光谱反射率；引入Boruta算法筛选了土壤Zn、Ni和Cu的特征波段。在此基础上，采用随机森林（RF）、极限学习机（ELM）、支持向量机（SVM）和人工神经网络（BPNN）算法构建了土壤Zn、Ni和Cu浓度和特征波段之间的定量反演模型，基于交叉验证方法和精度评价指标R²、RMSE和MAE评价了反演模型的稳定性和鲁棒性；最后基于最优反演模型，对GF-5号高光谱影像进行波段运算得到研究区土壤Zn、Ni和Cu浓度空间分布图，评估了利用GF-5号高光谱影像在较大范围准确、快速绘制土壤Zn、Ni和Cu含量的可行性。本文结果可为露天煤矿土壤重金属环境监测以及土壤修复提供数据支撑。本文主要研究结果如下：

 （1）CWT可以有效地消除或降低GF-5号高光谱影像数据噪声，Boruta算法在一定程度上消除了光谱数据冗余，可以有效地提取特征波段。土壤Zn的特征波段主要分布在480-677nm、827-1029nm、1241-1334nm、1435-1797nm和1949-2500nm范围内，Ni的特征波段集中于514-630nm、835-985nm、1258-1325nm、1460-1578nm和1949-2319nm范围内，Cu的特征波段主要分布在822-831nm、1029-1300nm、1486-1595nm和1730-2294nm；2000-2300nm光谱波长附近是土壤Zn、Ni和Cu共同的特征波段范围，具有普遍代表性。

（2）DS算法可有效校正GF-5号高光谱影像光谱反射率，很大程度上消除或降低了土壤水分等外部因素对野外光谱的干扰，进而提高模型估算精度。RF和ELM模型训练能力较好，在反演土壤重金属含量方法体现出一定的优势，Zn、Ni和Cu最优反演模型建模 R_c²分别为0.90、0.83和0.71验证 Rv²分别为0.77、0.62和0.56。

（3）土壤Zn、Ni和Cu含量的空间分布趋势与地面实测结果基本一致，总体呈现西南高东北低的变化趋势。露天煤矿附近的土壤重金属浓度相对较高，特别是在研究区东南部呈现较明显的大范围面状聚集分布；土壤Zn和Ni浓度整体未超土壤环境质量农用地土壤污染风险管控标准（GB15618-2018），但靠近矿区附近超过了当地土壤环境质量背景值。而靠近矿区的土壤Cu浓度超过风险筛选值，污染面积约为1.08km²，占整个研究区域的2%；GF-5号高光谱影像可作为在较大范围反演土壤重金属浓度可靠的卫星影像之一；此外，研究发现研究区土壤重金属聚集可能的主要原因为露天煤矿开采活动，车辆尾气排放、粉尘、废水和垃圾处理可能是研究区土壤重金属富集的其他原因。

       Quick and accurate obtaining spatial distribution of heavy metals concentrations is the premise and basis of pollution assessment, ecological restoration, land consolidation, and reclamation in the mining area. Traditional methods of soil heavy metal concentrations investigation and measurement are not only expensive, time-consuming, laborious, and easy to produce secondary pollution to the environment, but also difficult to meet the needs of large-scale Spatio-temporal dynamic monitoring. Spaceborne hyperspectral remotely sensed technology, gradually becoming a prevalent technology for soil heavy metals concentrations investigation, has the advantages of a wide monitoring range, strong band continuity, high spectral resolution, lower cost, and higher efficiency than traditional methods. Therefore, it has significant theoretical and practical value to use spaceborne hyperspectral remote sensing for obtaining soil heavy metals distribution in the mining area.

        In recent years, hyperspectral remotely sensed technology has been widely used in predicting soil heavy metals concentrations. However, most previous outcomes are limited to discrete sample scales under a relatively stable laboratory environment. Soil spectral information is affected not only by soil physical properties but also chemical properties (such as soil organic matter content and soil moisture, etc.) Moreover, soil spectra are considered mixed spectra because the field environment exists large uncertainties, which seriously affected the inversion accuracy. Therefore, using hyperspectral remotely sensed technology to retrieve soil heavy metal contents is still a great challenge and a hot topic all over the world.

       Given this, 110 soil samples were collected from an open-pit coal mine at the end of February 2020. The reflectance spectra of soil samples and the concentrations of zinc (Zn), Nickel (Ni), and Copper (Cu) of soil samples were surveyed by an ASD spectrometer and a portable X-ray fluorescence spectrometer (PXRF) in the laboratory. Meanwhile, GF-5 hyperspectral images of the study area were made available from the Aero Geophysical Survey and Remote Sensing Center of Natural Resources of China, and using spectral reflectance surveyed at the laboratory to correct GF-5 hyperspectral image through the direct correction algorithm (DS). Spectral reflectance of GF-5 hyperspectral image was reconstructed at different decomposition scales by continuous wavelet transform (CWT). Boruta algorithm was introduced to screen the characteristic bands of Zn, Ni, and Cu in soil. Furthermore, random forest (RF), extreme learning machine (ELM), support vector machine (SVM), and artificial neural network (BPNN) algorithms were used to construct quantitative inversion models between Zn, Ni, and Cu concentrations and characteristic bands. The stability and robustness of the inversion models were evaluated based on the cross-validation method and accuracy evaluation indexes R², RMSE, and MAE. Last but not least, the spatial distribution of soil Zn, Ni, and Cu concentrations were mapped by the optimal inversion model as well as using bands calculation for the GF-5 hyperspectral image. The results can provide data support for soil heavy metals monitoring and soil remediation at opencast coal mines. The main results of this paper were as follows:

(1) CWT can effectively eliminate or reduce the noise of GF-5 hyperspectral image, and the Boruta algorithm eliminated spectral data redundancy to a certain extent and could effectively extract feature bands. The characteristic bands of soil Zn are mainly distributed in the range of 480-677nm, 827-1029nm, 1241-1334nm, 1435-1797nm, and 1949-2500nm, respectively. The characteristic bands of Ni are concentrated in the range of 514-630nm, 835-985nm, 1258-1325nm, 1460-1578nm, and 1949-2319nm, respectively. The characteristic bands of Cu are mainly located at 822-831nm, 1029-1300nm, 1486-1595nm, and 1730-2294nm, respectively. The spectral wavelength of 2000nm-2300nm were common characteristic bands for soil Zn, Ni, and Cu, which the representation is significant.

(2) The DS algorithm could effectively calibrate the spectral reflectance of GF-5 hyperspectral images, eliminate or reduce the interference of soil moisture and other uncertainties on the field spectrum to a large extent, and improve the accuracy of the estimation model. The training ability of RF and ELM models, showing certain advantages in retrieving soil heavy metals contents, is well and acceptable. The R_c² of optimum inversion models for Zn, Ni, and Cu were 0.90, 0.83, and 0.71, respectively, and the R_v² were 0.77, 0.62, and 0.56, respectively.

(3) The spatial distribution trend of soil Zn, Ni, and Cu was basically consistent with the actual measured results, which were generally high in the southwest and low in the northeast. The concentrations of soil heavy metals were relatively high near the open-pit coal mine, especially in the southeast of the study area. Although the concentrations of Zn and Ni did not exceed the National soil environmental background values for agricultural land (GB15618-2018), were higher than the local soil environmental background values near the mining area. Cu concentrations exceeded the risk screening value near the mining area, and the contaminated area was about 1.08 km², accounting for 2% of the whole study area. GF-5 hyperspectral image could be used as one of the reliable satellite images for retrieving soil heavy metals concentrations in a large range. In addition, the study found that open-pit coal mining activities may be the main sources of soil heavy metals pollution in the mining area, and vehicle exhaust emissions, dust, wastewater, and garbage treatment may be other causes of soil heavy metals deposition in the study area.

[1] Chen R, De Sherbinin A. China’s Soil Pollution Farms on the Frontline[J]. Science, 2014, 344(6185): 691-693.

[2] Pan Y, Ding L, Xie S, et al. Spatiotemporal simulation, early warning, and policy recommendations of the soil heavy metal environmental capacity of the agricultural land in a typical industrial city in China: Case of Zhongshan City - ScienceDirect[J]. Journal of Cleaner Production, 2020, 285: 124849.

[3] Dai J, Lv P, Ma Z, et al. Environmental risk and housing price: An empirical study of Nanjing, China[J]. Journal of Cleaner Production, 2020, 252: 119828.

[4] Guo B, Su Y, Pei L, et al. Ecological risk evaluation and source apportionment of heavy metals in park playgrounds a case study in Xi’an, Shaanxi Province, a northwest city of China[J]. Environmental Science and Pollution Research, 2020, 27(19): 24400-24412.

[5] Wang F, Gao J, Zha Y. Hyperspectral sensing of heavy metals in soil and vegetation: Feasibility and challenges[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 136: 73-84.

[6] Ngole-Jeme V M. Heavy metals in soils along unpaved roads in south west Cameroon: Contamination levels and health risks[J]. Ambio, 2016, 3(45): 374-386.

[7] Guo B, Zhang B, Su Y, et al. Retrieving zinc concentrations in topsoil with reflectance spectroscopy at Opencast Coal Mine sites[J]. Scientific reports, 2021, 11(1): 19909.

[8] Lanphear B P, Rauch S, Auinger P, et al. Low-level lead exposure and mortality in US adults: a population-based cohort study[J]. The Lancet Public Health, 2018, 3(4): 177-184.

[9] Sun W, Zhang X, Sun X, et al. Predicting nickel concentration in soil using reflectance spectroscopy associated with organic matter and clay minerals[J]. Geoderma, 2018, 327: 25-35.

[10] Jiang X, Lu W X, Zhao H Q, et al. Potential ecological risk assessment and prediction of soil heavy-metal pollution around coal gangue dump[J]. Natural Hazards and Earth System Sciences, 2014, 2(3): 1977-2010.

[11] 苏海民, 孙朋, 张勇. 宿州市煤矿区土壤重金属地球化学基线及污染评价研究[J]. 环境污染与防治, 2021, 43(12): 1568-1572.

[12] 刘薇, 李媛, 李晶晶, 等. 煤矿城市典型区域土壤重金属分布特征及其变化[J]. 环境污染与防治, 2021, 43(8): 984-989.

[13] Zhang B, Guo B, Zou B, et al. Retrieving soil heavy metals concentrations based on GaoFen-5 hyperspectral satellite image at an opencast coal mine, Inner Mongolia, China[J]. Environmental pollution, 2022, 300: 118981.

[14] Fu P, Yang K, Meng F, et al. A new three-band spectral and metal element index for estimating soil arsenic content around the mining area[J]. Process Safety and Environmental Protection, 2022, 157: 27-36.

[15] 张秋霞, 张合兵, 刘文锴, 等. 高标准基本农田建设区域土壤重金属含量的高光谱反演[J]. 农业工程学报, 2017, 33(12): 230-239.

[16] 涂宇龙, 邹滨, 姜晓璐, 等. 矿区土壤Cu含量高光谱反演建模[J]. 光谱学与光谱分析, 2018, 38(2): 575-581.

[17] 成永生, 周瑶. 土壤重金属高光谱遥感定量监测研究进展与趋势[J]. 中国有色金属学报, 2021, 31(11): 18-48.

[18] Tan K, Ma W, Chen L, et al. Estimating the distribution trend of soil heavy metals in mining area from HyMap airborne hyperspectral imagery based on ensemble learning[J]. Journal of Hazardous Materials, 2021, 401: 123288.

[19] Butler O T, Cairns W R, Cook J M, et al. Atomic spectrometry update. Environmental analysis[J]. Journal of Analytical Atomic Spectrometry, 2012, 27: 187-2214.

[20] Shi T, Guo L, Chen Y, et al. Proximal and remote sensing techniques for mapping of soil contamination with heavy metals[J]. Applied spectroscopy reviews, 2018, 53(10): 783-805.

[21] Kalnicky D J, Singhvi R. Field portable XRF analysis of environmental samples[J]. Journal of Hazardous Materials, 2001, 83(1-2): 93-122.

[22] Hu B, Chen S, Hu J, et al. Application of portable XRF and VNIR sensors for rapid assessment of soil heavy metal pollution[J]. PLOS ONE, 2017, 12(2): 172438.

[23] Horta A, Malone B, Stockmann U, et al. Potential of integrated field spectroscopy and spatial analysis for enhanced assessment of soil contamination: A prospective review[J]. Geoderma, 2015, 241: 180-209.

[24] Wang D, Chakraborty S, Weindorf D C, et al. Synthesized use of VisNIR DRS and PXRF for soil characterization: Total carbon and total nitrogen[J]. Geoderma, 2015, 243: 157-167.

[25] Weindorf D C, Bakr N, Zhu Y. Advances in Portable X-ray Fluorescence (PXRF) for Environmental, Pedological, and Agronomic Applications[J]. Advances in agronomy, 2014, 128: 1-45.

[26] Kilbride C, Poole J, Hutchings T R. A comparison of Cu, Pb, As, Cd, Zn, Fe, Ni and Mn determined by acid extraction/ICP–OES and ex situ field portable X-ray fluorescence analyses[J]. Environmental Pollution, 2006, 143(1): 16-23.

[27] 杨桂兰, 倪晓芳, 张长波. 基于便携式X射线荧光光谱法的土壤重金属快速检测[J]. 浙江农业学报, 2019, 31(11): 1903-1908.

[28] 朱梦杰. 便携式XRF测定仪在土壤检测中的应用及其影响因素[J]. 中国环境监测, 2019, 35(6): 129-137.

[29] Radu T, Diamond D. Comparison of soil pollution concentrations determined using AAS and portable XRF techniques[J]. Journal of Hazardous Materials, 2009, 171(1-3): 1168-1171.

[30] 杨桂兰, 商照聪, 李良君, 等. 便携式X射线荧光光谱法在土壤重金属快速检测中的应用[J]. 应用化工, 2016, 45(8): 1586-1591.

[31] Malley D F, Williams P C. Use of Near-Infrared Reflectance Spectroscopy in Prediction of Heavy Metals in Freshwater Sediment by Their Association with Organic Matter[J]. Environmental science & technology, 1997, 31(12): 3461-3467.

[32] Rossel R, Adamchuk V I, Sudduth K A, et al. Proximal Soil Sensing: An Effective Approach for Soil Measurements in Space and Time[J]. Advances in Agronomy, 2011, 113: 243-291.

[33] 李志远, 邓帆, 贺军亮, 等. 土壤重金属砷的高光谱估算模型[J]. 光谱学与光谱分析, 2021, 41(9): 2872-2878.

[34] Jia X, O'Connor D, Shi Z, et al. VIRS based detection in combination with machine learning for mapping soil pollution[J]. Environmental Pollution, 2021, 268: 115845.

[35] Gholizadeh A, Saberioon M, Ben-Dor E, et al. Monitoring of selected soil contaminants using proximal and remote sensing techniques: Background, state-of-the-art and future perspectives[J]. Critical reviews in environmental science and technology, 2018, 48(3): 243-278.

[36] Zhao D, Wang J, Jiang X, et al. Reflectance spectroscopy for assessing heavy metal pollution indices in mangrove sediments using XGBoost method and physicochemical properties[J]. Catena, 2022, 211: 105967.

[37] Khosravi V, Doulati Ardejani F, Yousefi S, et al. Monitoring soil lead and zinc contents via combination of spectroscopy with extreme learning machine and other data mining methods[J]. Geoderma, 2018, 318: 29-41.

[38] 方少文, 杨梅花, 赵小敏, 等. 红壤区土壤有机质光谱特征与定量估算——以江西省吉安县为例[J]. 土壤学报, 2014, 51(5): 8.

[39] Douglas R K, Nawar S, Cipullo S, et al. Evaluation of vis-NIR reflectance spectroscopy sensitivity to weathering for enhanced assessment of oil contaminated soils[J]. Science of The Total Environment, 2018, 626: 1108-1120.

[40] 郭云开, 张思爱, 谢晓峰, 等. 基于GA-SVM的耕地土壤重金属含量高光谱反演方法的研究[J]. 土壤通报, 2021, 52(4): 968-974.

[41] 张霞, 王一博, 孙伟超, 等. 基于铁氧化物特征光谱和改进遗传算法反演土壤Pb含量[J]. 农业工程学报, 2020, 36(16): 103-109.

[42] 邹滨, 涂宇龙, 姜晓璐, 等. 土壤Cd含量实验室与野外DS光谱联合反演[J]. 光谱学与光谱分析, 2019, 39(10): 3223-3231.

[43] Song Y, Li F, Yang Z, et al. Diffuse reflectance spectroscopy for monitoring potentially toxic elements in the agricultural soils of Changjiang River Delta, China[J]. Applied Clay Science, 2012, 64: 75-83.

[44] Tan K, Wang H, Chen L, et al. Estimation of the spatial distribution of heavy metal in agricultural soils using airborne hyperspectral imaging and random forest[J]. Journal of Hazardous Materials, 2020, 382: 120987.

[45] Žížala D, Zádorová T, Kapička J. Assessment of Soil Degradation by Erosion Based on Analysis of Soil Properties Using Aerial Hyperspectral Images and Ancillary Data, Czech Republic[J]. Remote Sensing, 2017, 9(1): 28-52.

[46] Gomez C, Gholizadeh A, Borůvka L, et al. Using legacy data for correction of soil surface clay content predicted from VNIR/SWIR hyperspectral airborne images[J]. Geoderma, 2016, 276: 84-92.

[47] Meng X, Bao Y, Liu J, et al. Regional soil organic carbon prediction model based on a discrete wavelet analysis of hyperspectral satellite data[J]. International Journal of Applied Earth Observation and Geoinformation, 2020, 89: 102111.

[48] Yin F, Wu M, Liu L, et al. Predicting the abundance of copper in soil using reflectance spectroscopy and GF5 hyperspectral imagery[J]. International Journal of Applied Earth Observation and Geoinformation, 2021, 102: 102420.

[49] Jeong Y, Yu J, Wang L, et al. Bulk scanning method of a heavy metal concentration in tailings of a gold mine using SWIR hyperspectral imaging system[J]. International Journal of Applied Earth Observation and Geoinformation, 2021, 102: 102382.

[50] Sun W, Liu S, Zhang X, et al. Performance of hyperspectral data in predicting and mapping zinc concentration in soil[J]. Science of the total environment, 2022, 824: 153766.

[51] Liu Z, Lu Y, Peng Y, et al. Estimation of Soil Heavy Metal Content Using Hyperspectral Data[J]. Remote Sensing, 2019, 11(12): 1464-1490.

[52] 杨灵玉, 高小红, 张威, 等. 基于Hyperion影像植被光谱的土壤重金属含量空间分布反演——以青海省玉树县为例[J]. 应用生态学报, 2016, 27(6): 1775-1784.

[53] Ye B, Tian S, Cheng Q, et al. Application of Lithological Mapping Based on Advanced Hyperspectral Imager (AHSI) Imagery Onboard Gaofen-5 (GF-5) Satellite[J]. Remote Sensing, 2020, 12(23): 3990-4009.

[54] Meng X, Bao Y, Ye Q, et al. Soil Organic Matter Prediction Model with Satellite Hyperspectral Image Based on Optimized Denoising Method[J]. Remote Sensing, 2021, 13(12): 2273-2293.

[55] 梁德印, 安萌, 王啸虎, 等. 资源一号02D卫星高光谱相机系统指标论证及总体设计[J]. 航天器工程, 2020, 29(6): 26-34.

[56] Zou B, Jiang X, Feng H, et al. Multisource spectral-integrated estimation of cadmium concentrations in soil using a direct standardization and Spiking algorithm[J]. Science of The Total Environment, 2020, 701: 134890.

[57] Zhou W, Yang H, Xie L, et al. Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model[J]. Catena, 2021, 202: 105222.

[58] Lu Q, Wang S, Bai X, et al. Rapid inversion of heavy metal concentration in karst grain producing areas based on hyperspectral bands associated with soil components[J]. Microchemical Journal, 2019, 148: 404-411.

[59] Hong Y, Shen R, Cheng H, et al. Estimating lead and zinc concentrations in peri-urban agricultural soils through reflectance spectroscopy: Effects of fractional-order derivative and random forest[J]. Science of The Total Environment, 2019, 651: 1969-1982.

[60] 郭学飞, 曹颖, 焦润成, 等. 基于高光谱的北京铁矿区土壤重金属镍元素含量反演研究[J]. 土壤通报, 2021, 52(4): 960-967.

[61] 沈强, 张世文, 葛畅, 等. 矿业废弃地重构土壤重金属含量高光谱反演[J]. 光谱学与光谱分析, 2019, 39(4): 1214-1221.

[62] Sun W, Zhang X. Estimating soil zinc concentrations using reflectance spectroscopy[J]. International Journal of Applied Earth Observation and Geoinformation, 2017, 58: 126-133.

[63] Liu J, Han J, Xie J, et al. Assessing heavy metal concentrations in earth-cumulic-orthic-anthrosols soils using Vis-NIR spectroscopy transform coupled with chemometrics[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2020, 226: 117639.

[64] 方臣, 匡华, 周小娟, 等. 湖北恩施地区土壤重金属高光谱反演模型研究[J]. 环境科学与技术, 2021, 44(9): 154-159.

[65] 廖钦洪, 顾晓鹤, 李存军, 等. 基于连续小波变换的潮土有机质含量高光谱估算[J]. 农业工程学报, 2012, 28(23): 132-139.

[66] Zhang S, Shen Q, Nie C, et al. Hyperspectral inversion of heavy metal content in reclaimed soil from a mining wasteland based on different spectral transformation and modeling methods[J]. Spectrochimica Acta Part A: Molecular & Biomolecular Spectroscopy, 2019, 211: 349-400.

[67] Jiang Q, Liu M, Wang J, et al. Feasibility of using visible and near-infrared reflectance spectroscopy to monitor heavy metal contaminants in urban lake sediment[J]. Catena, 2018, 162: 72-79.

[68] 王雪梅, 玉米提·买明, 毛东雷, 等. 干旱区绿洲耕层土壤重金属铬含量的高光谱估测[J]. 生态环境学报, 2021, 30(10): 2076-2084.

[69] 袁自然, 魏立飞, 张杨熙, 等. 优化CARS结合PSO-SVM算法农田土壤重金属砷含量高光谱反演分析[J]. 光谱学与光谱分析, 2020, 40(2): 7.

[70] 任顺, 张雄, 任东, 等. 基于X射线荧光光谱与多特征串联策略的土壤重金属含量预测[J]. 分析测试学报, 2020, 39(7): 829-837.

[71] 陈元鹏, 张世文, 罗明, 等. 基于高光谱反演的复垦区土壤重金属含量经验模型优选[J]. 农业机械学报, 2019, 50(1): 170-179.

[72] Xu D, Chen S, Xu H, et al. Data fusion for the measurement of potentially toxic elements in soil using portable spectrometers[J]. Environmental Pollution, 2020, 263: 114649.

[73] Araújo M C U, Saldanha T C B, Galvão R K H, et al. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J]. Chemometrics and intelligent laboratory systems, 2001, 57(2): 65-73.

[74] 周茉, 邹滨, 涂宇龙, 等. 关联类标准化样品特征波段的矿区土壤重金属Pb高光谱反演[J]. 光谱学与光谱分析, 2020, 40(7): 2182-2187.

[75] Shi T, Hu X, Guo L, et al. Digital mapping of zinc in urban topsoil using multisource geospatial data and random forest[J]. Science of the total environment, 2021, 792: 148455.

[76] 马伟波, 谭琨, 李海东, 等. 基于超限学习机的矿区土壤重金属高光谱反演[J]. 生态与农村环境学报, 2016, 32(2): 213-218.

[77] Chen T, Chang Q, Clevers J G P W, et al. Rapid identification of soil cadmium pollution risk at regional scale based on visible and near-infrared spectroscopy[J]. Environmental Pollution, 2015, 206: 217-226.

[78] Dkhala B, Mezned N, Gomez C, et al. Hyperspectral field spectroscopy and SENTINEL-2 Multispectral data for minerals with high pollution potential content estimation and mapping[J]. Science of The Total Environment, 2020, 740: 140160.

[79] Ou D, Tan K, Lai J, et al. Semi-supervised DNN regression on airborne hyperspectral imagery for improved spatial soil properties prediction[J]. Geoderma, 2021, 385: 114875.

[80] 程朋根, 吴剑, 李大军, 等. 土壤有机质高光谱遥感和地统计定量预测[J]. 农业工程学报, 2009, 25(3): 142-155.

[81] Wang J, Cui L, Gao W, et al. Prediction of low heavy metal concentrations in agricultural soils using visible and near-infrared reflectance spectroscopy[J]. Geoderma, 2014, 216(4): 1-9.

[82] Cheng H, Shen R, Chen Y, et al. Estimating heavy metal concentrations in suburban soils with reflectance spectroscopy[J]. Geoderma, 2019, 336: 59-67.

[83] Shen Q, Xia K, Zhang S, et al. Hyperspectral indirect inversion of heavy-metal copper in reclaimed soil of iron ore area[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 222: 117191.

[84] 王金凤, 王世杰, 白晓永, 等. 基于高光谱反射率的喀斯特地区土壤重金属锌元素含量反演[J]. 光谱学与光谱分析, 2019, 39(12): 3873-3879.

[85] 宋婷婷, 付秀丽, 陈玉, 等. 云南个旧矿区土壤锌污染遥感反演研究[J]. 遥感技术与应用, 2018, 33(1): 88-95.

[86] Guan Q, Zhao R, Wang F, et al. Prediction of heavy metals in soils of an arid area based on multi-spectral data[J]. Journal of Environmental Management, 2019, 243: 137-143.

[87] Peng Y, Kheir R, Adhikari K, et al. Digital Mapping of Toxic Metals in Qatari Soils Using Remote Sensing and Ancillary Data[J]. Remote Sensing, 2016, 8(12): 1003-1021.

[88] Liu G, Zhou X, Li Q, et al. Spatial distribution prediction of soil As in a large-scale arsenic slag contaminated site based on an integrated model and multi-source environmental data[J]. Environmental Pollution, 2020, 267: 115631.

[89] Munnaf M A, Mouazen A M. Removal of external influences from on-line vis-NIR spectra for predicting soil organic carbon using machine learning[J]. Catena, 2022, 211: 106015.

[90] 李硕, 李春莲, 陈颂超, 等. 基于野外可见近红外光谱和水分影响校正算法的土壤剖面有机碳预测[J]. 光谱学与光谱分析, 2021, 41(4): 1234-1239.

[91] Ji W, Viscarra Rossel R A, Shi Z. Improved estimates of organic carbon using proximally sensed vis-NIR spectra corrected by piecewise direct standardization[J]. European Journal of Soil Science, 2015, 66(4): 670-678.

[92] Wijewardane N K, Ge Y, Morgan C L S. Moisture insensitive prediction of soil properties from VNIR reflectance spectra based on external parameter orthogonalization[J]. Geoderma, 2016, 267: 92-101.

[93] Ackerson J P, Demattê J A M, Morgan C L S. Predicting clay content on field-moist intact tropical soils using a dried, ground VisNIR library with external parameter orthogonalization[J]. Geoderma, 2015, 259-260: 196-204.

[94] Ji W, Li S, Chen S, et al. Prediction of soil attributes using the Chinese soil spectral library and standardized spectra recorded at field conditions[J]. Soil and Tillage Research, 2016, 155: 492-500.

[95] Zeng X, Liu Z, He C, et al. Quantifying Surface Coal-Mining Patterns to Promote Regional Sustainability in Ordos, Inner Mongolia[J]. Sustainability, 2018, 10(4): 1135-1152.

[96] Hou X, He Y, Jones B T. Recent Advances in Portable X‐Ray Fluorescence Spectrometry[J]. Applied Spectroscopy Reviews, 2004, 39(1): 1-25.

[97] Nawar S, Cipullo S, Douglas R K, et al. The applicability of spectroscopy methods for estimating potentially toxic elements in soils: state-of-the-art and future trends[J]. Applied Spectroscopy Reviews, 2019, 3(1): 1-33.

[98] 陈良富, 尚华哲, 范萌, 等. 高分五号卫星大气参数探测综述[J]. 遥感学报, 2021, 25(9): 1917-1931.

[99] 范渭亮, 杜华强, 周国模, 等. 大气校正对毛竹林生物量遥感估算的影响[J]. 应用生态学报, 2010, 21(1): 4-11.

[100] 童庆禧, 张兵, 张立福. 中国高光谱遥感的前沿进展[J]. 遥感学报, 2016, 20(5): 689-707.

[101] 刘梓钦, 赵世湖, 裴亮, 等. GF-5卫星高光谱数据大气校正反射率精度评价[J]. 遥感信息, 2021, 36(3): 93-98.

[102] Vermote E F, Tanre D, Deuze J L, et al. Second simulation of the satellite signal in the solar spectrum, 6S: An overview.[J]. IEEE Transactions on Geoscience & Remote Sensing, 1997, 35(3): 675.

[103] 马冯, 孙旭, 高连如, 等. "高分四号"卫星正射校正精度分析[J]. 航天返回与遥感, 2022, 40(1): 74-82.

[104] 张兵. 高光谱图像处理与信息提取前沿[J]. 遥感学报, 2016, 20(5): 1062-1090.

[105] 董桓宇. 高光谱图像解混技术的研究[D]. 重庆邮电大学, 2020.

[106] 何晓宁, 曹建农, 高坡, 等. 基于顶点成分分析法的端元提取改进算法[J]. 测绘通报, 2013, 6(7): 30-34.

[107] 李文昊宁鸿章谭鑫李宇航焦庆斌. 空-谱维联合Savitzky-Golay高光谱滤波算法及其应用[J]. 光谱学与光谱分析, 2020, 40(12): 3699-3704.

[108] Hong Y, Chen S, Chen Y, et al. Comparing laboratory and airborne hyperspectral data for the estimation and mapping of topsoil organic carbon: Feature selection coupled with random forest[J]. Soil and Tillage Research, 2020, 199: 104589.

[109] Khosravi V, Ardejani F D, Yousef S, et al. Monitoring soil lead and zinc contents via combination of spectroscopy with extreme learning machine and other data mining methods - ScienceDirect[J]. Geoderma, 2018, 318: 29-41.

[110] Guo B, Zhang D, Pei L, et al. Estimating PM2.5 concentrations via random forest method using satellite, auxiliary, and ground-level station dataset at multiple temporal scales across China in 2017[J]. Science of The Total Environment, 2021, 778: 146288.

[111] Smola A J, Lkopf B S. A tutorial on support vector regression[J]. Statistics and Computing, 2004, 14(3): 199-222.

[112] Xue Y, Zou B, Wen Y, et al. Hyperspectral Inversion of Chromium Content in Soil Using Support Vector Machine Combined with Lab and Field Spectra[J]. Sustainability, 2020, 12: 4441-4457.

[113] Wang X, Zhang F, Kung H T, et al. New methods for improving the remote sensing estimation of soil organic matter content (SOMC) in the Ebinur Lake Wetland National Nature Reserve (ELWNNR) in northwest China[J]. Remote Sensing of Environment, 2018, 218: 104-118.

[114] Cheng W, Lei S, Bian Z, et al. Geographic distribution of heavy metals and identification of their sources in soils near large, open-pit coal mines using positive matrix factorization[J]. Journal of Hazardous Materials, 2020, 387: 121666.

[115] Shi T, Chen Y, Liu Y, et al. Visible and near-infrared reflectance spectroscopy—An alternative for monitoring soil contamination by heavy metals[J]. Journal of Hazardous Materials, 2014, 265: 166-176.

[116] Ji W, Viscarra Rossel R A, Shi Z. Accounting for the effects of water and the environment on proximally sensed vis-NIR soil spectra and their calibrations[J]. European Journal of Soil Science, 2015, 66(3): 555-565.

[117] Hong Y, Chen S, Chen Y, et al. Comparing laboratory and airborne hyperspectral data for the estimation and mapping of topsoil organic carbon: Feature selection coupled with random forest[J]. Soil and Tillage Research, 2020, 199: 104589.

[118] 郭云开, 谢晓峰, 谢琼, 等. 基于小波变换的土壤重金属铬含量定量反演[J]. 测绘工程, 2021, 30(3): 66-71.