Traditional water quality detection methods will consume a lot of manpower and material resources. However, remote sensing data and field water quality monitoring data are used to establish water quality remote sensing inversion model to achieve water quality remote sensing monitoring, which makes up for the shortcomings of traditional methods and can monitor the water quality environment comprehensively, quickly and dynamically. However, due to the impact of objective conditions, field water quality data is difficult to obtain in large quantities, so machine learning theory is used, A large number of easily obtained remote sensing image(RSI) data can effectively solve the problem of water quality monitoring. In this experiment, 50 polluted RSIs and 50 unpolluted RSIs are used to extract the gray distribution features of RSIs as the features of the training set. The parameters of GBDT model were optimized, and the accuracy of identifying polluted and unpolluted areas reached 98.67%. In addition, by comparing the performance of three machine learning algorithms, GBDT, DT and SVM, it is found that GBDT algorithm has the highest accuracy in RSI classification. The use of GBDT algorithm enables us to automatically monitor the pollution in RSIs without any marks, which realizes the automation of pollution monitoring.

Ilankoon Raymond. Machine Learning Algorithm for Background Analysis of Remote Sensing Image Pollution Monitoring. Water Pollution Prevention and Control Project (2023), Vol. 4, Issue 2: 18-25. https://doi.org/10.38007/WPPCP.2023.040203.

[1] Priyanka, N. Sravya, Shyam Lal , J. Nalini, Chintala Sudhakar Reddy, Fabio DellAcqua: DIResUNet. Architecture for multiclass semantic segmentation of high resolution RSIry data. Appl. Intell. (2022) 52(13): 15462-1 5482. https://doi.org/10.1007/s10489-022-03310-z

[2] Tran Manh Tuan, Tran Thi Ngan, Nguyen Tu Trung. Object Detection in Remote Sensing lmages Using Picture Fuzzy Clustering and MapReduce. Comput. Syst. Sci. Eng. (2022) 43(3): 1241-1253. https://doi.org/10.32604/csse.2022.024265

[3] K. Kala, N. Padmasini, B. Suresh Chander Kapali, P. G. Kuppusamy. A new framework for object detection using fastcnn- Naive Bayes classifier for RSI extraction. Earth Sci. Informatics. (2022) 15(3): 1779-1787. https://doi.org/10.1007/s12145-022-00834-3

[4] A. Azhagu Jaisudhan Pazhani, S. Periyanayagi. A novel haze removal computing architecture for RSIs using multi-scale Retinex technique. Earth Sci. Informatics. (2022) 15(2): 1147-1154. https://doi.org/10.1007/s12145-022-00798-4

[5] Samuel A. Ajila, Chung-Horng Lung, Anurag Das. Analysis of error-based machine learning algorithms in network anomaly detection and categorization. Ann. des Telecommunications. (2022) 77(5-6): 359-370. https://doi.org/10.1007/s12243-021-00836-0

[6] Koushiki Dasgupta Chaudhuri, Bugra Alkan. A hybrid extreme learning machine model with harris hawks optimisation algorithm: an optimised model for product demand forecasting applications. Appl. Intell. (2022) 52(10): 11489-11505. https://doi.org/10.1007/s10489-022-03251-7

[7] Paul D. Rosero-Montalvo, Vivian F. Lopez Batista, Ricardo P. Arciniega-Rocha, Diego Hernan Peluffo-Ordonez. Air Pollution Monitoring Using WSN Nodes with Machine Learning Techniques: A Case Study. Log. J. IGPL. (2022) 30(4): 599-610. https://doi.org/10.1093/jigpal/jzab005

[8] Davut Ari, Baris Baykant Alagoz. An effective integrated genetic programming and neural network model for electronic nose calibration of air pollution monitoring application. Neural Comput. Appl. (2022) 34(15): 12633-12652. https://doi.org/10.1007/s00521-022-07129-0

[9] Ekta Dixit, Vandana Jindal. IEESEP: an intelligent energy efficient stable election routing protocol in air pollution monitoring WSNs. Neural Comput. Appl. (2022) 34(13): 10989-11013. https://doi.org/10.1007/s00521-022-07027-5

[10] Yiannis N. Kontos, Theodosios Kassandros, Konstantinos Perifanos, Marios Karampasis, Konstantinos L. Katsifarakis, Kostas D. Karatzas. Machine learning for groundwater pollution source identification and monitoring network optimization. Neural Comput. Appl. (2022) 34(22): 19515-19545. https://doi.org/10.1007/s00521-022-07507-8

[11] Juan Jesus Roldan-Gomez, Pablo Garcia Aunon, Pablo Mazariegos, Antonio Barrientos. SwarmCity project: monitoring traffic, pedestrians, climate, and pollution with an aerial robotic swarm. Pers. Ubiquitous Comput. (2022) 26(4): 1151-1167. https://doi.org/10.1007/s00779-020-01379-2

[12] Mowva Pavani, K. Kishore Kumar. Large scale air pollution monitoring using static multi-hop wireless sensor networks. Int. J. Comput. Aided Eng. Technol. (2021) 15(2/3): 294-305 . https://doi.org/10.1504/IJCAET.2021.117139

[13] Pau Ferrer-Cid, Jose M. Barcel6-Ordinas, Jorge Garcia-Vidal. Graph Learning Techniques Using Structured Data for IoT Air Pollution Monitoring Platforms. IEEE Internet Things J. (2021) 8(17): 13652-13663. https://doi.org/10.1109/JIOT.2021.3067717

[14] Huber Flores, Naser Hossein Motlagh, Agustin Zuniga, Mohan Liyanage, Monica Passananti, Sasu Tarkoma, Moustafa Youssef, Petteri Nurmi. Toward Large-Scale Autonomous Marine Pollution Monitoring. IEEE Internet Things Mag. (2021) 4(1): 40-45.  https://doi.org/10.1109/IOTM.0011.2000057

[15] Swati Chopade, Hari Prabhat Gupta, Rahul Mishra, Preti Kumari, Tanima Dutta. An Energy-Efficient River Water Pollution Monitoring System in Internet of Things. IEEE Trans. Green Commun. Netw. (2021) 5(2): 693- 702. https://doi.org/10.1109/TGCN.2021.3062470

[16] Aayushi Gautam, Gaurav Verma, Shamimul Qamar, Sushant Shekhar. Vehicle Pollution Monitoring, Control and Challan System Using MQ2 Sensor Based on Internet of Things. Wirel. Pers. Commun 11. (2021) 6(2): 1071-1085. https://doi.org/10.1007/s11277-019-06936-4

[17] Vahid Sadeghi, Hossein Etemadfard. Optimal cluster number determination of FCM for unsupervised change detection in RSIs. Earth Sci. Informatics. (2022) 15(2): 1045-1057. https://doi.org/10.1007/s12145-021-00757-5

[18] Rajni Sharma, M. Ravinder, Nitin Sharma, Kanchan Sharma. An optimal RSI enhancement with weak detail preservation in wavelet domain. J. Ambient Intell. Humaniz. Comput. (2022) 13(4): 1941-1 952. https://doi.org/10.1007/s12652-021-02957-9