Ji Jingjing,Bai Liying,She Dongli,et al.Comparative Study on Retrieval Model of Dissolved N2O Concentration in Drainage Ditch Based on GF-1 Satellite Remote Sensing[J].Research of Soil and Water Conservation,2024,31(05):257-264.[doi:10.13869/j.cnki.rswc.2024.05.035]
基于GF-1卫星遥感反演排水河沟水体溶存N2O浓度模型对比研究
- Title:
- Comparative Study on Retrieval Model of Dissolved N2O Concentration in Drainage Ditch Based on GF-1 Satellite Remote Sensing
- 文章编号:
- 1005-3409(2024)05-0257-08
- Keywords:
- N2O concentration; GF-1 satellite; inversion; machine learning
- 分类号:
- X87
- 文献标志码:
- A
- 摘要:
- [目的]探究利用GF-1卫星数据反演水体溶存氧化亚氮(N2O)浓度的可行性,为实现低成本、高效率的水质实时监测提供有效途径。[方法]以宁夏青铜峡灌区第1和第5排水河沟为研究对象,选取与排水河沟水体溶存N2O浓度相关性高的GF-1卫星影像波段反射率和水质参数作为自变量,通过最优子集筛选法确定最优自变量组合,分别构建了多元线性回归、BP神经网络和支持向量机模型,对水体溶存N2O浓度进行预测对比。[结果]水温(T)、溶解性有机碳(DOC)等是影响水体溶存N2O浓度的主要因素,同时近红外(NIR)等卫星波段与水体溶存N2O浓度变化趋势显著相关。当自变量包括T,NIR等7个因素时,模型预测效果最佳。在3种模型中,BP神经网络模型验证结果R2为0.64,具有最高预测精度。[结论]GF-1卫星数据以及水质参数与水体溶存N2O浓度存在复杂的相关性关系,且BP神经网络能够实现利用GF-1卫星数据较高精度地反演水体溶存N2O浓度。
- Abstract:
- [Objective]The aims of this study are to explore the feasibility of using GF-1 satellite data to retrieve the concentration of dissolved nitrous oxide(N2O)in water, so as to provide an effective way to realize low-cost and high-efficiency real-time monitoring of water quality. [Methods]The 1st and 5th drainage ditches in Qingtongxia Irrigation District of Ningxia were selected as the research objects, and the reflectance and water quality parameters of GF-1 satellite image band, which were highly correlated with the concentration of dissolved N2O in the drainage ditches, were selected as independent variables, and the optimal combination of independent variables was determined by optimal subset screening method. Multiple linear regression, BP neural network and support vector machine models were respectively constructed to predict and compare the concentration of dissolved N2O in water. [Results]The water temperature(T)and dissolved organic carbon(DOC)were the main factors affecting the concentration of dissolved N2O in water, and satellite bands such as near infrared(NIR)were significantly correlated with the variation trend of dissolved N2O concentration in water. When the independent variable including 7 factors such as T and NIR, the model had the best prediction effect. Among the three models, the R2 of BP neural network model was 0.64, which had the highest prediction accuracy. [Conclusion]There is a complex correlation between GF-1 satellite data and water quality parameters and dissolved N2O concentration in water bodies, and BP neural network can use GF-1 satellite data to retrieve dissolved N2O concentration in water bodies with high accuracy.
参考文献/References:
[1]谭永洁,王东启,周立旻,等.河流氧化亚氮产生和排放研究综述[J].地球与环境,2015,43(1):123-132.
Tan Y J, Wang D Q, Zhou L M, et al. Review on the production and emission of nitrous oxide from rivers[J]. Earth and Environment, 2015,43(1):123-132.
[2]王安吉,马文林,吴建繁,等.2015—2019年北京市农业氧化亚氮排放变化与分析[J].中国农业资源与区划,2023,44(1):47-56.
Wang A J, Ma W L, Wu J F, et al. Changes and analysis of agricultural nitrous oxide emission in Beijing from 2015 to 2019[J]. Chinese Journal of Agricultural Resources and Regional Planning, 2023,44(1):47-56.
[3]赵松,侯毅凯,张安兵,等.基于无人机多光谱影像的滏阳河水质遥感反演[J].测绘与空间地理信息,2022,45(3):81-85.
Zhao S, Hou Y K, Zhang A B, et al. Remote sensing inversion of water quality of Fuyang River based on UAV multi-spectral images[J]. Geomatics & Spatial Information Technology, 2022,45(3):81-85.
[4]赵琳.基于长时序多光谱遥感技术的白洋淀水质演变监测分析[J].现代信息科技,2023,7(5):141-144.
Zhao L. Monitoring and analysis of water quality evolution in Baiyang lake based on long time series multispectral remote sensing technology[J]. Modern Information Technology, 2023,7(5):141-144.
[5]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,2020,41(8):3591-3600.
Huang X X, Ying H T, Xia K, et al. Inversion of water quality parameters based on UAV multispectral images and the OPT-MPP algorithm[J]. Environmental Science, 2020,41(8):3591-3600.
[6]祁兰兰,王金亮,农兰萍,等.基于GF-1卫星数据的洱海干季水质时空变化监测[J].人民长江,2021,52(9):24-31.
Qi L L, Wang J L, Nong L P, et al. Temporal and spatial monitoring on water quality of Erhai lake in dry season based on GF-1 satellite data[J]. Yangtze River, 2021,52(9):24-31.
[7]彭保发,陈哲夫,李建辉,等.基于GF-1影像的洞庭湖区水体水质遥感监测[J].地理研究,2018,37(9):1683-1691.
Peng B F, Chen Z F, Li J H, et al. Monitoring water quality of Dongting lake region based on GF-1 image[J]. Geographical Research, 2018,37(9):1683-1691.
[8]Lin S, Novitski L N, Qi J, et al. Landsat TM/ETM+and machine-learning algorithms for limnological studies and algal bloom management of inland lakes[J]. Journal of Applied Remote Sensing, 2018,12(2):1-17.
[9]Chang N B, Xuan Z M, Yang Y J. Exploring spatiotemporal patterns of phosphorus concentrations in a coastal bay with MODIS images and machine learning models[J]. Remote Sensing of Environment, 2013,134:100-110.
[10]Zheng Z B, Li Y M, Guo Y L, et al. Landsat-based long-term monitoring of total suspended matter concentration pattern change in the wet season for Dongting lake, China[J]. Remote Sensing, 2015,7:13975-13999.
[11]Xiao X, Xu J, Hu C F, et al. Assessment of water quality in natural river based on HJ1A/1B CCD multi-spectral remote sensing data[C]//Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications V. Beijing, China. Spie,2014,9263:270-283.
[12]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,2022,53(1):195-205.
Liu M, Ma Q L, Yuan J L, et al. Water quality monitoring of inland aquaculture ponds based on UAV hyperspectral remote sensing technology[J]. Oceanologia Et Limnologia, 2022,53(1):195-205.
[13]魏艳芳.青铜峡灌区排水沟农业非点源污染物分布特征及贡献率研究[D].银川:宁夏大学,2019.
Wei Y F. Study on conventional pollution transport in drainage ditch of Qingtongxia irrigation area and its contribution rate to drainage ditch[D]. Yinchuan:Ningxia University, 2019.
[14]Xia Y Q, Li Y F, Ti C P, et al. Is indirect N2O emission a significant contributor to the agricultural greenhouse gas budget:A case study of a rice paddy-dominated agricultural watershed in Eastern China[J]. Atmospheric Environment, 2013,77:943-950.
[15]Miyashiro R, Takano Y. Mixed integer second-order cone programming formulations for variable selection in linear regression[J]. European Journal of Operational Research, 2015,247(3):721-731.
[16]Liu G, Wu M Q, Niu Z, et al. Investigation method for crop area using remote sensing sampling based on GF-1 satellite data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(5):160-166.
[17]姚一飞,王爽,张珺锐,等.基于GF-1卫星遥感的河套灌区土壤含水率反演模型研究[J].农业机械学报,2022,53(9):239-251.
Yao Y F, Wang S, Zhang J R, et al. Inversion model of soil moisture in Hetao irrigation district based on GF-1 satellite remote sensing[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022,53(9):239-251.
[18]Qin X H, Zheng L L. Mathematical models for analysis of water pollution[J]. Applied Mechanics and Materials, 2012, 209:1941-1947.
[19]Liu K L, Lin T, Zhong T T, et al. New methods based on a genetic algorithm back propagation(GABP)neural network and general regression neural network(GRNN)for predicting the occurrence of trihalomethanes in tap water[J]. Science of the Total Environment, 2023,870:161976.
[20]冯汉中,杨淑群,刘波.支持向量机(SVM)方法在气象预报中的个例试验[J].四川气象,2005,25(2):9-12.
Feng H Z, Yang S Q, Liu B. A case study of support vector machine(SVM)method in meteorological forecast[J]. Journal of Sichuan Meteorology, 2005,25(2):9-12.
[21]Okcu D, Pektas A O, Uyumaz A. Creating a non-linear total sediment load formula using polynomial best subset regression model[J]. Journal of Hydrology, 2016,539:662-673.
[22]张智韬,韩佳,王新涛,等.基于全子集-分位数回归的土壤含盐量反演研究[J].农业机械学报,2019,50(10):142-152.
Zhang Z T, Han J, Wang X T, et al. Soil salinity inversion based on best subsets-quantile regression model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019,50(10):142-152.
[23]祝令亚.湖泊水质遥感监测与评价方法研究[D].北京:中国科学院遥感应用研究所,2006.
Zhu L Y. Remote sensing monitoring and assessment of water quality for lakes[D]. Beijing:Institute of Remote Sensing Applications, Chinese Academy of Sciences, 2006.
[24]徐红敏.基于支持向量机理论的水环境质量预测与评价方法研究[D].长春:吉林大学,2007.
Xu H M. Study on the prediction and assessment methods of water environment quality based on support vector machines theory[D]. Changchun:Jilin University, 2007.
[25]徐敏.基于复杂性理论的河湖环境系统模型研究[D].长沙:湖南大学,2007.
Xu M. Research of water environmental system models based oncomplexity theory[D]. Changsha:Hunan University, 2007.
[26]王渤权,金传鑫,周论,等.基于长短期记忆网络的西丽水库水质预测[J].长江科学院院报,2023,40(6):64-70.
Wang B Q, Jin C X, Zhou L, et al. Water quality prediction for Xili reservoir based on long-short term memory[J]. Journal of Changjiang River Scientific Research Institute, 2023,40(6):64-70.
备注/Memo
收稿日期:2023-09-14 修回日期:2023-10-20
资助项目:国家自然科学基金“海涂盐碱地农业汇水区反硝化和厌氧氨氧化脱氮机制与过程拟”(42177393)
第一作者:嵇晶晶(2000—),女,江苏宿迁人,硕士研究生,主要从事农业水土工程研究。E-mail:jijingjing836@163.com
通信作者:佘冬立(1980—),男,湖南长沙人,博士,教授,博士生导师,主要从事农业生态与水土过程模拟研究。E-mail:shedongli@hhu.edu.cn