Remote Sensing Inversion of Water Quality Parameters of Dapu River in Lianyungang Based on Machine Learning Method

Abstract

Abstract: This study takes parts of Dapu River and Dapu vice River in Lianyungang City as the study area,and conducts research and analysis on water pollution through field measured data and UAV hyperspectral remote sensing images. Multi- layer perceptron （MLP） is used to construct the prediction and inversion model of water quality parameters for UAV hyperspectral data processing,and K-Fold cross-validation is used. The coefficient of determination （R²） between the predicted values of ammonia nitrogen and total phosphorus and the measured values is higher than 0.8,and the mean absolute percentage error （MAPE） is less than 15%. The R² of permanganate index is 0.58,because its numerical range is small,but the overall prediction effect is ideal,the MAPE is only about 2%,and the inversion effect is good. Finally,the current situation of pollution sources and the main water environment problems of the target reach are analyzed and discussed through the inversion results.

Key words: UAV, hyperspectral, machine learning, water quality parameters, remote sensing inversion

CLC Number:

WANG Jingshun, CHEN Ying, ZHANG Yue, XU Xiangkai, HE Chao, HE Miao. Remote Sensing Inversion of Water Quality Parameters of Dapu River in Lianyungang Based on Machine Learning Method[J]. TIANJIN SCIENCE & TECHNOLOGY, 2023, 50(9): 66-72.

References

[1] 任万平,李晓秀,张汪寿. 沉积物中磷形态及影响其释放的环境因素研究进展[J]. 环境污染与防治,2012,34(9):53-60,66.
[2] 吴晓东,刘炜伟,任晨曦,等. 沂沭泗水系新沭河下段现状行洪能力分析[J]. 中国防汛抗旱,30(12):39-43.
[3] 刘梅,马启良,原居林,等. 基于无人机高光谱遥感技术对内陆养殖池塘水质监测的研究[J]. 海洋与湖沼,2022(1):195-205.
[4] 高泽东,郝群,刘宇,等. 高光谱成像与应用技术发展[J]. 计测技术,2019, 39(4):24-34.
[5] 葛明锋. 基于轻小型无人机的高光谱成像系统研究[D]. 北京:中国科学院大学,2015.
[6] 庄华,陈扬骎,季文海,等. 可见光波段水分子离子吸收光谱的测量[J]. 科学通报,2001,46(15):1251-1254.
[7] 白羽. 基于自适应 NDVI 阈值的青岛海域浒苔监测研究[D]. 青岛:中国石油大学(华东),2014.
[8] 韩玲. 基于人工神经网络——多层感知器(MLP) 的遥感影像分类模型[J]. 测绘通报,2004(9):29-30,42.
[9] 束美艳,陈向阳,王喜庆,等. 基于高光谱数据的玉米叶面积指数和生物量评估[J]. 智慧农业,2021,3(15):29-39.
[10] 陈俊英,邢正,张智韬,等. 基于高光谱定量反演模型的污水综合水质评价[J]. 农业机械学报,2019,50(11):200-209.
[11] 杨振,卢小平,武永斌,等. 无人机高光谱遥感的水质参数反演与模型构建[J]. 测绘科学,2020,45(9):60-64,95.
[12] 黄昕晰,应晗婷,夏凯,等. 基于无人机多光谱影像和 OPT-MPP 算法的水质参数反演[J]. 环境科学,2020(8):3591-3600.
[13] Gitelson A,Szilagyi F,Mittenzwey K H.Improving quantitative remote sensing for monitoring of inland water quality[J]. Water research, 1993,27(7):1185-1194.
[14] 骆剑承,周成虎,杨艳. 人工神经网络遥感影像分类模型及其与知识集成方法研究[J]. 遥感学报,2001,5(2):122-129.
[15] 彭海龙,冯倩. 基于多层感知器的卫星散射计海面风速反演研究[C] //深圳:第二届微波遥感技术研讨会摘要全集,2006.
[16] 王美雅,徐涵秋. 超大城市土地覆盖与热环境的随机森林回归模型研究[J]. 遥感技术与应用,2022,37(2):379-388.
[17] 刘艳慧,蔡宗磊,包妮沙,等. 基于无人机大样方草地植被覆盖度及生物量估算方法研究[J]. 生态环境学报,2018,27(11): 2023-2032.
[18] 岳程鹏,李兴,包龙山,等. 基于Landsat8 OLI 遥感数据反演乌梁素海浮游植物生物量[J]. 灌溉排水学报,2020,39(8):122-128.
[19] 梅安新,彭望琭,秦其明,等. 遥感导论[M]. 北京:高等教育出版社,2001.
[20] 刘彦君,夏凯,冯海林,等. 基于无人机多光谱影像的小微水域水质要素反演[J]. 环境科学学报,2019,39(4):1241-1249.
[21] 胡震天,周源. 基于低空多光谱遥感的城市水质监测方法研究[J]. 地理空间信息,2020,18(7):4-8.
[22] Romero-Trigueros C,Nortes P A, Alarcón J J, et al.Effects of saline reclaimed waters and deficit irrigation on Citrus physiology assessed by UAV remote sensing[J]. Agricultural water management, 2017(183):60-69.