|
|
光谱反演技术在环境监测应用中的关键挑战与趋势展望
|
Abstract:
光谱反演技术通过解析污染介质对电磁波的吸收、反射和散射规律，实现污染物浓度、组分及生态相关指标的定量化估算，是现代环境遥感监测体系的核心方法。近年来，随着高光谱卫星(如GF-5、PRISMA、EnMAP)、机载高光谱传感器以及无人机搭载超高分辨率光谱系统的迅速发展，环境污染光谱反演的研究快速发展，从传统的经验统计模型、光谱指数方法，到数据驱动的机器学习模型、深度学习网络，再到物理–数据融合模型体系，光谱反演技术正从“基于经验”向“基于机理与智能”方向系统演变。然而，环境污染反演仍受到光谱混合效应强、污染介质异质性复杂、辐射传输模型不确定性大、多源数据尺度不一致、模型跨场景泛化能力不足等问题制约。根据文献和未来管理应用场景需求，本文认为未来的发展方向包括：构建深度耦合物理意义的智能反演模型，实现跨区域与跨季节的稳健预测；发展高时间分辨率与高空间分辨率的多源、跨尺度融合方法，实现水体、大气、土壤污染过程的连续监测；利用边缘计算与卫星在轨处理能力，推动环境污染遥感反演向实时化、智能化发展。
Spectral inversion techniques quantify pollutant concentrations, compositions, and ecology-related indicators by analyzing the absorption, reflection, and scattering characteristics of contaminated media to electromagnetic radiation. As a core methodology in modern environmental remote-sensing systems, spectral inversion has advanced rapidly in recent years with the development of hyperspectral satellites (e.g., GF-5, PRISMA, EnMAP), airborne sensors, and ultra-high-resolution UAV-mounted spectrometers. Research now encompasses a progression from traditional empirical and spectral-index-based approaches to data-driven machine-learning and deep-learning models, and further to emerging physics–data hybrid frameworks. This evolution reflects a broader shift from “experience-based” to “mechanism- and intelligence-based” paradigms. However, environmental pollution inversion remains constrained by strong spectral-mixing effects, pronounced heterogeneity in polluted media, substantial uncertainties in radiative-transfer modeling, scale inconsistencies across multi-source data, and limited cross-scene model generalization. Based on existing literature and anticipated management needs, we argued that future developments should include constructing physically grounded intelligent inversion models capable of robust prediction across regions and seasons; developing multi-source, cross-scale fusion methods with high temporal and spatial resolution to enable continuous monitoring of water, atmospheric, and soil pollution; and leveraging edge computing and on-orbit satellite processing to advance environmental pollution inversion toward real-time and intelligent applications.
| [1] | Fuller, R., Landrigan, P.J., Balakrishnan, K., Bathan, G., Bose-O’Reilly, S., Brauer, M., et al. (2022) Pollution and Health: A Progress Update. The Lancet Planetary Health, 6, e535-e547. https://doi.org/10.1016/s2542-5196(22)00090-0 |
| [2] | Oliveira, C. (2024) Air, Water and Soil Pollution: Integrative Approaches to Mitigation. Pollution, 7, Article 346. |
| [3] | Wang, S. and Qin, B. (2023) Research Progress on Remote Sensing Monitoring of Lake Water Quality Parameters. Environmental Science, 44, 1228-1243. |
| [4] | 彭涛. 基于机载高光谱遥感的土壤主要养分反演[D]: [硕士学位论文]. 保定: 河北农业大学, 2024. |
| [5] | Münzel, T., Hahad, O., Daiber, A. and Landrigan, P.J. (2022) Soil and Water Pollution and Human Health: What Should Cardiologists Worry about? Cardiovascular Research, 119, 440-449. https://doi.org/10.1093/cvr/cvac082 |
| [6] | Zhou, S.H. and Lin, R.P. (2019) Spatial-Temporal Heterogeneity of Air Pollution: The Relationship between Built Environment and On-Road PM2.5 at Micro Scale. Transportation Research Part D: Transport and Environment, 76, 305-322. https://doi.org/10.1016/j.trd.2019.09.004 |
| [7] | Chen, C. and Wen, Z.G. (2023) Cross-Media Transfer of Nitrogen Pollution in the Fast-Urbanized Greater Bay Area of China: Trends and Essential Control Paths. Journal of Environmental Management, 326, Article 116796. https://doi.org/10.1016/j.jenvman.2022.116796 |
| [8] | Long, Q., Ma, J., Guo, C., Wang, M. and Wang, Q. (2025) High-Resolution Spatio-Temporal Estimation of Street-Level Air Pollution Using Mobile Monitoring and Machine Learning. Journal of Environmental Management, 377, Article 124642. https://doi.org/10.1016/j.jenvman.2025.124642 |
| [9] | 李俊生, 吴迪, 吴远峰, 等. 基于实测光谱数据的太湖水华和水生高等植物识别[J]. 湖泊科学, 2009, 21(2): 215-222. |
| [10] | 吴季友. 新时期生态环境遥感监测发展思路与举措[J]. 环境与可持续发展, 2024(3): 21-25. |
| [11] | 陈潜. 基于高光谱数据的土壤含水量反演[J]. 长江信息通信, 2024, 41(12): 19-22. |
| [12] | 王世瑞, 沈芳, 魏小岛. Sentinel-2/MSI深度学习超分辨率重建及河湖水质遥感反演[J]. 遥感信息, 2023, 38(3): 16-23. |
| [13] | Deng, Y., Zhang, Y., Pan, D., Yang, S.X. and Gharabaghi, B. (2024) Review of Recent Advances in Remote Sensing and Machine Learning Methods for Lake Water Quality Management. Remote Sensing, 16, Article 4196. https://doi.org/10.3390/rs16224196 |
| [14] | Assaf, M.N., Abdelal, Q., Hussein, N.M., Halaweh, G. and Alzubaidi, A.J. (2025) Water Quality Monitoring and Management: Integration of Machine Learning Algorithms and Sentinel-2 Images for the Estimation of Chlorophyll-A. Modeling Earth Systems and Environment, 11, Article No. 348. https://doi.org/10.1007/s40808-025-02543-4 |
| [15] | Xu, S., Li, S., Tao, Z., Song, K., Wen, Z., Li, Y., et al. (2022) Remote Sensing of Chlorophyll-A in Xinkai Lake Using Machine Learning and GF-6 WFV Images. Remote Sensing, 14, Article 5136. https://doi.org/10.3390/rs14205136 |
| [16] | Jiang, Y., Kong, J., Zhong, Y., Zhang, J., Zheng, Z., Wang, L., et al. (2023) The Optimal Method for Water Quality Parameters Retrieval of Urban River Based on Machine Learning Algorithms Using Remote Sensing Images. International Journal of Remote Sensing, 45, 7297-7317. https://doi.org/10.1080/01431161.2023.2209918 |
| [17] | Kwon, D.H., Ahn, J.M., Pyo, J.C., Lee, J., Abbas, A., Park, S., et al. (2025) Probabilistic Machine Learning-Based Phytoplankton Estimation from Hyperspectral Airborne Remote Sensing. International Journal of Remote Sensing, 62, Article 2464864. |
| [18] | Ramtel, P., Feng, D. and Gardner, J. (2024) Toward Large-Scale Riverine Phosphorus Estimation Using Remote Sensing and Machine Learning. Journal of Geophysical Research: Biogeosciences, 129, e2024JG008121. https://doi.org/10.1029/2024jg008121 |
| [19] | Ngamile, S., Kganyago, M., Madonsela, S., et al. (2025) Characterising the Spatio-Temporal Patterns of Water Quality Parameters in the Cradle of Humankind World Heritage Site using Sentinel-2 MSI and Random Forest Regressor. Frontiers in Remote Sensing, 6, Article 1631403. |
| [20] | Zhang, L., Ma, C., Chen, X., et al. (2025) An Integrated Algorithm to Estimate Chlorophyll-A Concentration in Various Optical Waters Using the HY-3A Coastal Zone Imager. ISPRS Journal of Photogrammetry and Remote Sensing, 210, 34-49. |
| [21] | Cui, J., Fang, L., Wu, Y., et al. (2025) Satellite Retrieval of Total Phosphorus Concentration in Lake Taihu Using Sentinel-2 Imagery and an Optimized XGBoost Model. Ecological Indicators, 175, Article 113563. |
| [22] | Deng, R., Zhu, T., Zhou, W., Liu, F. and Lin, X. (2025) Machine Learning Based Water Quality Evolution and Pollution Identification in Reservoir Type Rivers. Environmental Pollution, 382, Article 126668. https://doi.org/10.1016/j.envpol.2025.126668 |
| [23] | Zhao, Y., Chen, M., He, J. and Ma, Y. (2025) Monitoring Water Quality Parameters Using Multi-Source Data-Driven Machine Learning Models. Engineering Applications of Computational Fluid Mechanics, 19, Article 2509658. https://doi.org/10.1080/19942060.2025.2509658 |
| [24] | Kutser, T., Verpoorter, C., Paavel, B. and Tranvik, L.J. (2015) Estimating Lake Carbon Fractions from Remote Sensing Data. Remote Sensing of Environment, 157, 138-146. https://doi.org/10.1016/j.rse.2014.05.020 |
| [25] | Schweitzer, G. (2024) Remote Sensing for Water Quality Monitoring in Oligotrophic Rivers Using Satellite-Based Data and Machine-Learning. Master’s Thesis, Mälardalen University, Västerås. |
| [26] | Deshmukh, S.L., Wilchek, M. and Batarseh, F.A. (2025) Hydro Vision: Predicting Optically Active Parameters in Surface Water Using Computer Vision. https://arxiv.org/abs/2509.01882 |
| [27] | Schweitzer, G., et al. (2024) Machine Learning Algorithms for Estimating Water Quality Parameters from Sentinel-2 Multispectral Data in Urban Rivers. Sustainability, 16, Article 6881. https://doi.org/10.3390/su16166881 |
| [28] | Yotam, S., Bar, E., Gabriel, R. and Moshe, H. (2025) Global Chlorophyll-A Retrieval Algorithm from Sentinel-2 Using Residual Deep Learning and Water Classification. |
| [29] | Si, W., Chen, Z., Jim, C.Y., Tan, M.L., Liu, D., Yao, Y., et al. (2025) Resolving Inherent Constraints in Eutrophication Monitoring of Small Lakes Using Multi-Source Satellites and Machine Learning. npj Clean Water, 8, 1-12. https://doi.org/10.1038/s41545-025-00525-8 |
| [30] | Liang, Y.C., Ding, F.Y., Liu, L., Yin, F., Hao, M.M., et al. (2025) Monitoring Water Quality Parameters in Urban Rivers Using Multi-Source Data and Machine Learning Approach. Science of the Total Environment, 648, Article 132394. |
| [31] | Mohan, S., Kumar, B. and Nejadhashemi, A.P. (2025) Integration of Machine Learning and Remote Sensing for Water Quality Monitoring and Prediction: A Review. Sustainability, 17, Article 998. https://doi.org/10.3390/su17030998 |
| [32] | Jeong, B., Lee, S., Heo, J., Lee, J. and Lee, M. (2025) Deep Learning-Based Retrieval of Chlorophyll-A in Lakes Using Sentinel-1 and Sentinel-2 Satellite Imagery. Water, 17, Article 1718. https://doi.org/10.3390/w17111718 |
| [33] | Yang, H., Du, Y., Zhao, H. and Chen, F. (2022) Water Quality Chl-A Inversion Based on Spatio-Temporal Fusion and Convolutional Neural Network. Remote Sensing, 14, Article 1267. https://doi.org/10.3390/rs14051267 |
| [34] | Li, J., Wang, J., Wu, Y., Cui, Y. and Yan, S. (2022) Remote Sensing Monitoring of Total Nitrogen and Total Phosphorus Concentrations in the Water around Chaohu Lake Based on Geographical Division. Frontiers in Environmental Science, 10, Article 1014155. https://doi.org/10.3389/fenvs.2022.1014155 |
| [35] | Cao, Z., Ma, R., Duan, H., Pahlevan, N., Melack, J., Shen, M., et al. (2020) A Machine Learning Approach to Estimate Chlorophyll-A from Landsat-8 Measurements in Inland Lakes. Remote Sensing of Environment, 248, Article 111974. https://doi.org/10.1016/j.rse.2020.111974 |
| [36] | Ruescas, A.B., Hieronymi, M., Mateo-Garcia, G., Koponen, S., Kallio, K. and Camps-Valls, G. (2018) Machine Learning Regression Approaches for Colored Dissolved Organic Matter (CDOM) Retrieval with S2-MSI and S3-OLCI Simulated Data. Remote Sensing, 10, Article 786. https://doi.org/10.3390/rs10050786 |
| [37] | Platt, U. and Stutz, J. (2008) Differential Optical Absorption Spectroscopy: Principles and Applications. Springer. |
| [38] | Richter, A., Burrows, J.P., Nüß, H., Granier, C. and Niemeier, U. (2005) Increase in Tropospheric Nitrogen Dioxide over China Observed from Space. Nature, 437, 129-132. https://doi.org/10.1038/nature04092 |
| [39] | Zhang, C., Liu, C., Chan, K.L., Hu, Q., Liu, H., Li, B., et al. (2020) First Observation of Tropospheric Nitrogen Dioxide from the Environmental Trace Gases Monitoring Instrument Onboard the Gaofen-5 Satellite. Light: Science & Applications, 9, Article 66. https://doi.org/10.1038/s41377-020-0306-z |
| [40] | Theys, N., De Smedt, I., Van Roozendael, M., et al. (2015) Sulfur Dioxide Vertical Column Retrievals from OMI: Algorithm Description and Validation. Atmospheric Measurement Techniques, 8, 903-921. |
| [41] | Boersma, K.F., Eskes, H.J. and Brinksma, E.J. (2004) Error Analysis for Tropospheric NO2 Retrieval from Space. Journal of Geophysical Research: Atmospheres, 109, D04311. https://doi.org/10.1029/2003jd003962 |
| [42] | Zhao, F., Liu, C., Hu, Q., Xia, C., Zhang, C. and Su, W. (2024) High Spatial Resolution Ozone Profiles Retrieved from the First Chinese Ultraviolet-Visible Hyperspectral Satellite Instrument. Engineering, 32, 106-115. https://doi.org/10.1016/j.eng.2023.02.020 |
| [43] | Veefkind, J.P., Aben, I., McMullan, K., Förster, H., de Vries, J., Otter, G., et al. (2012) TROPOMI on the ESA Sentinel-5 Precursor: A GMES Mission for Global Observations of the Atmospheric Composition for Climate, Air Quality and Ozone Layer Applications. Remote Sensing of Environment, 120, 70-83. https://doi.org/10.1016/j.rse.2011.09.027 |
| [44] | Corradino, C., Jouve, P., La Spina, A. and Del Negro, C. (2024) Monitoring Earth’s Atmosphere with Sentinel-5 TROPOMI and Artificial Intelligence: Quantifying Volcanic SO2 Emissions. Remote Sensing of Environment, 315, Article 114463. https://doi.org/10.1016/j.rse.2024.114463 |
| [45] | Seo, S., Valks, P., Lutz, R., Heue, K., Hedelt, P., Molina García, V., et al. (2024) Tropospheric NO2 Retrieval Algorithm for Geostationary Satellite Instruments: Applications to Gems. Atmospheric Measurement Techniques, 17, 6163-6191. https://doi.org/10.5194/amt-17-6163-2024 |
| [46] | Zoogman, P., Heald, C.L. and Krotkov, N.A. (2021) TEMPO: Tropospheric Emissions Monitoring of Pollution. Journal of Atmospheric and Oceanic Technology, 38, 1239-1254. |
| [47] | Mali, P., Biswas, M.S., Beirle, S., Wagner, T., Hulswar, S., Inamdar, S., et al. (2024) Aerosol Measurements over India: Comparison of MAX-DOAS Measurements with Ground-Based (AERONET) and Satellite-Based (MODIS) Data. Aerosol and Air Quality Research, 24, Article 230076. https://doi.org/10.4209/aaqr.230076 |
| [48] | Holben, B.N., Eck, T.F., Slutsker, I., Tanré, D., Buis, J.P., Setzer, A., et al. (1998) AERONET—A Federated Instrument Network and Data Archive for Aerosol Characterization. Remote Sensing of Environment, 66, 1-16. https://doi.org/10.1016/s0034-4257(98)00031-5 |
| [49] | Tian, X., Xie, P., Xu, J., Li, A., Wang, Y., Qin, M., et al. (2018) Long-Term Observations of Tropospheric NO2, SO2 and HCHO by MAX-DOAS in Yangtze River Delta Area, China. Journal of Environmental Sciences, 71, 207-221. https://doi.org/10.1016/j.jes.2018.03.006 |
| [50] | Spurr, R.J.D. (2006) VLIDORT: A Linearized Pseudo-Spherical Vector Discrete Ordinate Radiative Transfer Code for Forward Model and Retrieval Studies in Multilayer Multiple Scattering Media. Journal of Quantitative Spectroscopy and Radiative Transfer, 102, 316-342. https://doi.org/10.1016/j.jqsrt.2006.05.005 |
| [51] | Rozanov, V.V., Buchwitz, M., Eichmann, K.-U., de Beek, R., Burrows, J.P. (2002) SCIATRAN—A New Radiative Transfer Model for Geophysical Applications in the 240-2400 nm Spectral Region: The Pseudo-Spherical Version. Advances in Space Research, 29, 1831-1835. https://doi.org/10.1016/S0273-1177(02)00095-9 |
| [52] | Liu, Y., Sarnat, J.A., Kilaru, V., Jacob, D.J. and Koutrakis, P. (2005) Estimating Ground-Level Pm2.5 in the Eastern United States Using Satellite Remote Sensing. Environmental Science & Technology, 39, 3269-3278. https://doi.org/10.1021/es049352m |
| [53] | Di, Q., Wang, Y., Zanobetti, A., Wang, Y., Koutrakis, P., Choirat, C., et al. (2017) Air Pollution and Mortality in the Medicare Population. New England Journal of Medicine, 376, 2513-2522. https://doi.org/10.1056/nejmoa1702747 |
| [54] | Li, T., Wang, Y. and Wu, J. (2024) Deriving PM2.5 from Satellite Observations with Spatiotemporally Weighted Tree-Based Algorithms: Enhancing Modeling Accuracy and Interpretability. npj Climate and Atmospheric Science, 7, Article 138. https://doi.org/10.1038/s41612-024-00692-4 |
| [55] | Deng, F., Chen, Y., Liu, W., Li, L., Chen, X., Tiwari, P., et al. (2024) Satellite-Based Estimation of Near-Surface NO2 Concentration in Cloudy and Rainy Areas. Remote Sensing, 16, Article 1785. https://doi.org/10.3390/rs16101785 |
| [56] | Yang, Q., Yuan, Q., Gao, M. and Li, T. (2023) A New Perspective to Satellite-Based Retrieval of Ground-Level Air Pollution: Simultaneous Estimation of Multiple Pollutants Based on Physics-Informed Multi-Task Learning. Science of The Total Environment, 857, Article 159542. https://doi.org/10.1016/j.scitotenv.2022.159542 |
| [57] | Norbert Bodendorfer. (2025) A HEART for the Environment: Transformer-Based Spatiotemporal Modeling for Air Quality Prediction. arXiv:2502.19042. https://doi.org/10.48550/arXiv.2502.19042 |
| [58] | Chen, C., Qiu, A., Chen, H., Chen, Y., Liu, X. and Li, D. (2023) Prediction of Pollutant Concentration Based on Spatial-temporal Attention, Resnet and ConvLSTM. Sensors, 23, Article 8863. https://doi.org/10.3390/s23218863 |
| [59] | Varey, J., Ruprecht, J.D., Tierney, M. and Sullenberger, R. (2024). Physics-informed Neural Networks for Satellite State Estimation. 2024 IEEE Aerospace Conference, Big Sky, 2-9 March 2024, 1-8. https://doi.org/10.1109/aero58975.2024.10521414 |
| [60] | Zhang, T., Zheng, B. and Huang, R. (2025) Adaptive High-Resolution Mapping of Air Pollution with a Novel Implicit 3D Representation Approach. npj Climate and Atmospheric Science, 8, Article 180. https://doi.org/10.1038/s41612-025-01044-6 |
| [61] | He, T., Jones, D.B.A., Miyazaki, K., Bowman, K.W., Jiang, Z., Chen, X., et al. (2022) Inverse Modelling of Chinese NOx Emissions Using Deep Learning: Integrating in Situ Observations with a Satellite-Based Chemical Reanalysis. Atmospheric Chemistry and Physics, 22, 14059-14074. https://doi.org/10.5194/acp-22-14059-2022 |
| [62] | Wu, P., Shen, H., Zhang, L. and Göttsche, F. (2015) Integrated Fusion of Multi-Scale Polar-Orbiting and Geostationary Satellite Observations for the Mapping of High Spatial and Temporal Resolution Land Surface Temperature. Remote Sensing of Environment, 156, 169-181. https://doi.org/10.1016/j.rse.2014.09.013 |
| [63] | Hameed, S., Islam, A., Ahmad, K., Belhaouari, S.B., Qadir, J. and Al-Fuqaha, A. (2023) Deep Learning Based Multimodal Urban Air Quality Prediction and Traffic Analytics. Scientific Reports, 13, Article 22181. https://doi.org/10.1038/s41598-023-49296-7 |
| [64] | Edwards, D.P., Martínez-Alonso, S., Jo, D.S., Ortega, I., Emmons, L.K., Orlando, J.J., et al. (2024) Quantifying the Diurnal Variation in Atmospheric NO2 from Geostationary Environment Monitoring Spectrometer (GEMS) Observations. Atmospheric Chemistry and Physics, 24, 8943-8961. https://doi.org/10.5194/acp-24-8943-2024 |
| [65] | Kuhn, L., Beirle, S., Osipov, S., Pozzer, A. and Wagner, T. (2024) NitroNet—A Deep-Learning NO2 Profile Retrieval Prototype for the TROPOMI Satellite Instrument. EGUsphere. https://doi.org/10.5194/egusphere-2024-1196 |
| [66] | 李清泉, 卢艺, 胡水波, 等. 海岸带地理环境遥感监测综述[J]. 遥感学报, 2016, 20(5): 1216-1229. |
| [67] | 肖洁芸, 周伟, 石佩琪. 土壤重金属含量高光谱反演[J]. 生态环境学报, 2023, 32(1): 175-182. |
| [68] | 柏晗. 基于多/高光谱影像的矿区土壤重金属含量反演方法研究[D]: [硕士学位论文]. 西安: 长安大学, 2022. |
| [69] | 王光羽, 杨斌, 魏添翼, 等. 采用高光谱技术的川西矿区周边土壤铬含量反演模型[J]. 华侨大学学报(自然科学版), 2025, 46(4): 462-469. |
| [70] | 梁永刚, 杨金燕. 高光谱土壤成分反演的特征波段提取研究进展[J]. 传感器与微系统, 2025, 44(11): 7-11+97. |
| [71] | 殷子瑶, 李俊生, 范海生, 等. 珠海一号高光谱卫星的于桥水库水质参数反演初步研究[J]. 光谱学与光谱分析, 2021, 41(2): 494-498. |
| [72] | Abdelbaki, A., Milewski, R., Saberioon, M., Berger, K., Demattê, J.A.M. and Chabrillat, S. (2025) Radiative Transfer Model-Integrated Approach for Hyperspectral Simulation of Mixed Soil-Vegetation Scenarios and Soil Organic Carbon Estimation. Remote Sensing, 17, Article 2355. https://doi.org/10.3390/rs17142355 |
| [73] | Yang, Y., Wang, Z., Cao, C., Xu, M., Yang, X., Wang, K., et al. (2024) Estimation of PM2.5 Concentration across China Based on Multi-Source Remote Sensing Data and Machine Learning Methods. Remote Sensing, 16, Article 467. https://doi.org/10.3390/rs16030467 |
