基于机器学习的卫星遥感水质富营养化评价——以合肥市环城河为例

doi:10.3969/j.issn.1000-5641.2024.01.001

华东师范大学学报（自然科学版） ›› 2024, Vol. 2024 ›› Issue (1): 1-8, 112.doi: 10.3969/j.issn.1000-5641.2024.01.001

• 水环境评价与修复治理 • 下一篇

基于机器学习的卫星遥感水质富营养化评价——以合肥市环城河为例

张勇^1,²(), 王慧^1,³, 朱传华¹, 周浩¹, 詹宇¹, 李灿¹, 肖逸凡¹, 杨丽丽¹, 刘佳奇¹

1. 安徽建筑大学环境与能源工程学院, 合肥　230601
2. 安徽建筑大学环境污染控制与废弃物资源化利用安徽省重点实验室, 合肥　230601
3. 荆州水务集团有限公司, 湖北荆州　434000

收稿日期:2023-04-26 接受日期:2023-10-20 出版日期:2024-01-25 发布日期:2024-01-23
作者简介:张　勇, 男, 教授, 硕士生导师, 研究方向为水处理技术. E-mail: zhangy@ahjzu.edu.cn
基金资助:
中国科学院科技服务网络计划 (KFJ-STS-QYZD-173); 安徽省高校自然科学研究项目 (KJ2021A0619)

Evaluation of eutrophication by satellite remote sensing based on machine learning: A case study of Huancheng River in Hefei

Yong ZHANG^1,²(), Hui WANG^1,³, Chuanhua ZHU¹, Hao ZHOU¹, Yu ZHAN¹, Can LI¹, Yifan XIAO¹, Lili YANG¹, Jiaqi LIU¹

1. School of Environmental and Energy Engineering, Anhui Jianzhu University, Hefei　230601, China
2. Anhui Provincial Key Laboratory of Environmental Pollution Control and Resource Reuse, Anhui Jianzhu University, Hefei　230601, China
3. Jingzhou Water Group Co. Ltd., Jingzhou, Hubei　434000, China

Received:2023-04-26 Accepted:2023-10-20 Online:2024-01-25 Published:2024-01-23

摘要/Abstract

摘要：

以合肥市环城河为研究对象, 使用线性回归、随机森林、支持向量回归和套索回归等机器学习模型挖掘Landsat8卫星数据和水质参数之间的关系, 对遥感影像值的反射率和水质参数进行建模, 并比较了4种不同模型的表现. 结果显示, 随机森林模型的表现最好, 对TN、TP、NH₃-N反演模型的精度都能达到0.7以上; 反演的水质参数浓度分布图表明TN、TP在环城河东北段的污染最严重, 而NH₃-N则在西南段的污染最严重; 从水体富营养化分布图可以看出, 环城河东段水体呈现中度营养状态.

关键词: 机器学习, Landsat8, 富营养化评价

Abstract:

Taking Huancheng River in Hefei City as the study site, machine learning models such as linear regression, random forest, support vector regression, and lasso regression were utilized to establish the relationship between Landsat8 satellite data and water quality parameters, model the reflectance and water quality parameters of remote sensing image values, and compare the performance of four different models. Results showed that the random forest model performed best, and the accuracy of the inversion models for total nitrogen (TN), total phosphorus (TP), and ammonia nitrogen (NH₃-N) was above 0.7. The concentration distribution map of water quality parameters showed that the pollution of TN and TP was the most significant in the northeast section of Huancheng River, while NH₃-N was most present in the southwest section. The water eutrophication distribution map shows that the water body in the eastern section of the Huancheng River showed a moderate nutrition state.

Key words: machine learning, Landsat8, eutrophication evaluation

中图分类号:

X824

张勇, 王慧, 朱传华, 周浩, 詹宇, 李灿, 肖逸凡, 杨丽丽, 刘佳奇. 基于机器学习的卫星遥感水质富营养化评价——以合肥市环城河为例[J]. 华东师范大学学报（自然科学版）, 2024, 2024(1): 1-8, 112.

Yong ZHANG, Hui WANG, Chuanhua ZHU, Hao ZHOU, Yu ZHAN, Can LI, Yifan XIAO, Lili YANG, Jiaqi LIU. Evaluation of eutrophication by satellite remote sensing based on machine learning: A case study of Huancheng River in Hefei[J]. Journal of East China Normal University(Natural Science), 2024, 2024(1): 1-8, 112.

图/表 10

图1

图2

表1

图3

表2

图4

图5

表3

表4

图6

参考文献 24

1	ADUSEI Y Y, QUAYE-BALLARD J, ADJAOTTOR A A, et al.. Spatial prediction and mapping of water quality of Owabi reservoir from satellite imageries and machine learning models. The Egyptian Journal of Remote Sensing and Space Sciences, 2021, 24 (3): 825- 833.
2	SHARAF E D E, ZHANG Y, ALAELDIN S.. Mapping concentrations of surface water quality parameters using a novel remote sensing and artificial intelligence framework. International Journal of Remote Sensing, 2017, 38 (4): 1023- 1042.
3	KRISHNARAJ A, HONNASIDDAIAH R.. Remote sensing and machine learning based framework for the assessment of spatio-temporal water quality in the Middle Ganga Basin. Environmental Science and Pollution Research, 2022, 27 (29): 64939- 64958.
4	SAGAN V, PETERSON K T, MAIMAITIJIANG M, et al.. Monitoring inland water quality using remote sensing: Potential and limitations of spectral indices, bio-optical simulations, machine learning, and cloud computing. Earth-Science Reviews, 2020, 205, 103187.
5	CHEN J, FU R, CHEN S, et al. Remote sensing big data for water environment monitoring: Current status, challenges, and future prospects [J]. Earth’s Future, 2022, 10(2): e2021EF002289.
6	JIANG Q O, XU L D, WANG M L, et al.. Retrieval model for total nitrogen concentration based on UAV hyper spectral remote sensing data and machine learning algorithms – A case study in the Miyun Reservoir, China. Ecological Indicators, 2021, 124, 107356.
7	WU C F, WU J P, Qi J G, et al.. Empirical estimation of total phosphorus concentration in the mainstream of the Qiantang River in China using Landsat TM data. International Journal of Remote Sensing, 2010, 21 (9): 2309- 2324.
8	ZHAO Y B, YU T, HU B L, et al.. Retrieval of water quality parameters based on near-surface remote sensing and machine learning algorithm. Remote Sensing, 2022, 14 (21): 5305.
9	王延军, 徐敏, 孟凡生, 等.. 长江中游黄盖湖富营养化趋势分析及原因诊断. 湖泊科学, 2023, 35 (4): 1- 14.
10	HE Y, GONG Z, ZHENG Y, et al.. Inland reservoir water quality inversion and eutrophication evaluation using BP neural network and remote sensing imagery: A case study of Dashahe Reservoir. Water, 2021, 13 (20): 2844.
11	生态环境部. 水质总氮的测定碱性过硫酸钾消解紫外分光光度法: HJ 636-2012 [S]. 北京: 中国环境科学出版社, 2012.
12	生态环境部. 水质氨氮的测定纳氏试剂分光光度法: HJ 535-2009 [S]. 北京: 中国环境科学出版社, 2009.
13	生态环境部. 水质总磷的测定钼酸铵分光光度法: GB11893-89 [S]. 北京: 中国标准出版社, 1989.
14	GUO R, DENG R R, LI J Y, et al.. Remote sensing retrieval of total nitrogen in the Pearl River Delta based on Landsat8. Water, 2022, 14 (22): 3710.
15	PANDIS N.. Correlation and linear regression. American Journal of Orthodontics and Dentofacial Orthopedics, 2016, 149 (2): 299.
16	TIAN S, GUO H, XU W, et al.. Remote sensing retrieval of inland water quality parameters using Sentinel-2 and multiple machine learning algorithms. Environmental Science and Pollution Research, 2022, 30, 18617- 18630.
17	XIAO X, ZHANG T, ZHONG X, et al.. Support vector regression snow-depth retrieval algorithm using passive microwave remote sensing data. Remote Sensing of Environment, 2018, 210, 48- 64.
18	NAJAFZADEH M, NIAZMARDI S.. A novel multiple-kernel support vector regression aigorithm for estimation of water quality parameters. Natural Resources Research, 2021, 30, 3761- 3775.
19	SHEN H, MA Y, LIN C, et al.. Hierarchical Bayesian support vector regression with model parameter calibration for reliability modeling and prediction. Reliability Engineering and System Safety, 2021, 206, 107268.
20	LEE J H, SHI Z, GAO Z.. On LASSO for predictive regression. Journal of Econometrics, 2021, 229 (2): 322- 349.
21	魏广芬, 李梦递, 赵捷.. 基于 DFI-RSE 电子鼻传感器阵列优化的葡萄酒 SO₂检测. 农业工程学报, 2022, 38 (7): 291- 299.
22	GHOSH S M, BEHERA M D.. Aboveground biomass estimation using multi-sensor data synergy and machine learning algorithms in a dense tropical forest. Applied Geography, 2018, 96, 29- 40.
23	殷飞. 水体营养状况评价方法研究 [J]. 科技创新与应用, 2017, 30: 99-100.
24	陈昭明, 王伟, 赵迎.. 三峡水库支流水体富营养化现状及防治策略. 环境工程, 2019, 37 (4): 32- 37.

水质参数	R²				MSE
水质参数	线性回归	随机森林	支持向量回归	套索回归	线性回归	随机森林	支持向量回归	套索回归
TN	–1147.4	0.971	–1.122	0.69	54422.29	1.39	100.56	14.79
TP	–1512.3	0.978	0.475	–0.23	236.52	0.01	0.08	0.19
NH₃-N	–484.6	0.910	–1.488	0.285	9917.83	1.84	50.81	14.60

反演模型	类型	公式	R²	MSE
TN	线性	y = 0.9652 x + 3.5371	0.8877	80.82
TP	线性	y = 1.2057 x + 0.2063	0.7475	0.28
NH₃-N	线性	y = 1.0840 x + 0.0537	0.7485	5.43

评分值M	富营养程度
M<30	贫营养
30≤M≤50	中营养
50<M≤60	轻营养
60<M≤70	中度富营养
M>70	重度富营养

位置点号	TN /(mg·L^–1)	TP /(mg·L^–1)	NH₃-N /(mg·L^–1)	评分值 M	评价结果
1	5.71	0.40	5.17	50.00	中营养
2	3.15	0.13	3.67	53.33	轻度富营养
3	5.93	0.23	2.61	53.33	轻度富营养
4	6.41	0.57	3.68	53.33	轻度富营养
5	2.36	0.29	0.78	50.00	中营养
6	4.24	0.32	0.59	70.00	中度富营养
7	16.18	1.07	0.85	70.00	中度富营养
8	18.47	1.11	0.91	70.00	中度富营养
9	13.07	0.90	0.21	70.00	中度富营养
10	11.62	0.50	0.06	40.00	中营养

[1]	高祥云, 孟丹, 罗明凯, 王俊, 张丽平, 孔超. 支持隐私保护的端云协同训练[J]. 华东师范大学学报（自然科学版）, 2023, 2023(5): 77-89.
[2]	周童晖, 柳银萍. 利用机器学习技术确定同伦分析解中的收敛控制参数[J]. 华东师范大学学报（自然科学版）, 2022, 2022(2): 34-44.
[3]	杨梦晨, 陈旭栋, 蔡鹏, 倪葎. 早期时间序列分类方法研究综述[J]. 华东师范大学学报（自然科学版）, 2021, 2021(5): 115-133.
[4]	余阳, 胡卉芪, 周煊. 基于非易失性内存的LSM-tree存储系统优化[J]. 华东师范大学学报（自然科学版）, 2021, 2021(5): 37-47.
[5]	肖垚, 毕军芳, 韩易, 董启文. 在线广告中点击率预测研究[J]. 华东师范大学学报(自然科学版), 2017, 2017(5): 80-86,100.

基于机器学习的卫星遥感水质富营养化评价——以合肥市环城河为例

Evaluation of eutrophication by satellite remote sensing based on machine learning: A case study of Huancheng River in Hefei

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 24

相关文章 5

编辑推荐

Metrics

本文评价