| Citation: |
PAN Wei, MI Wu-Juan, ZHANG Yu-Heng, HUANG Yu-Bo, TIAN Chu-Ming, JING Xiao-Xuan, ZHU Yu-Xuan, BI Yong-Hong, LI Yuan. OPTIMIZATION OF BP NEURAL NETWORK FOR CHLOROPHYLL-A CONCENTRATION INVERSION BASED ON SPARROW SEARCH ALGORITHM: A CASE STUDY OF XIAOJIANG[J]. ACTA HYDROBIOLOGICA SINICA. DOI: 10.7541/2025.2024.0484
|
Chlorophyll-a concentration is a crucial parameter characterizing water ecological environment quality. To address the issues of traditional Back Propagation (BP) neural networks, which are highly sensitive to initial values and tendency to local optima in chlorophyll-a inversion, this study proposes an SSA-BP inversion model optimized by using the Sparrow Search Algorithm (SSA). A novel inversion model was constructed by integrating remote sensing data from the DJI RTK300 UAV equipped with an AFX-10hyperspectral camera and synchronous ground sampling data from the Xiaojiang backwater area. The results demonstrate that: (1) The application of Savitzky-Golay (SG) smoothing significantly improved spectral data quality, increasing the determination coefficient (R2) of the SSA-BP model to 0.98; (2) Compared with traditional BP neural networks, the SSA-BP model showed comprehensive improvement in inversion accuracy, with the Quma water area exhibiting a 59.14% reduction in Mean Absolute Error (MAE), 60.78% decrease in Root Mean Square Error of Prediction (RMSEP), and 57.32% increase in Relative Percent Difference (RPD); (3) The SSA-BP model overcame the performance degradation of traditional BP models in low-concentration regions (where R2 decreased from 0.94 to 0.76), maintaining stable high precision across different chlorophyll-a concentration gradients, with the highest R2 reaching 0.98. This research confirms that the SSA-BP model significantly enhances the accuracy and adaptability of UAV hyperspectral remote sensing in chlorophyll-a inversion, providing a reliable technical approach for ecological environment monitoring in inland water bodies.
| [1] |
Mishra S, Mishra D R. Normalized difference chlorophyll index: A novel model for remote estimation of chlorophyll-a concentration in turbid productive waters [J]. Remote Sensing of Environment, 2012(117): 394-406.
|
| [2] |
罗婕纯一, 秦龙君, 毛鹏, 等. 水质遥感监测的关键要素叶绿素a的反演算法研究进展 [J]. 遥感技术与应用, 2021, 36(3): 473-488.]
Luo J C Y, Qin L J, Mao P, et al. Research progress in the retrieval algorithms for chlorophyll-a, a key element of water quality monitoring by remote sensing [J]. Remote Sensing Technology and Application, 2021, 36(3): 473-488. [
|
| [3] |
李泽军. 从水体叶绿素含量评价于桥水库富营养化程度 [J]. 河北水利水电技术, 2001(6): 44-45.]
Li Z J. Rich nutrition estimate of Yuqiao reservoir from the content of water body chlorobhyll [J]. Hebei Water Sciences and Engineering Technology, 2001(6): 44-45. [
|
| [4] |
陈艳, 刘绥华, 王堃, 等. 基于Landsat卫星影像的草海水质遥感反演及营养状态评价 [J]. 水生态学杂志, 2020, 41(3): 24-31.]
Chen Y, Liu S H, Wang K, et al. Remote sensing of Caohai Lake water quality using landsat satellite images [J]. Journal of Hydroecology, 2020, 41(3): 24-31. [
|
| [5] |
沈蔚, 纪茜, 邱耀炜, 等. 基于高光谱遥感的长江口叶绿素a浓度反演推算 [J]. 水生态学杂志, 2021, 42(3): 1-6.]
Shen W, Ji Q, Qiu Y W, et al. Estimation of chlorophyll-a concentrations in the Yangtze River Estuary obtained from hyperspectral remote sensing images [J]. Journal of Hydroecology, 2021, 42(3): 1-6. [
|
| [6] |
王思梦, 秦伯强. 湖泊水质参数遥感监测研究进展 [J]. 环境科学, 2023, 44(3): 1228-1243.]
Wang S M, Qin B Q. Research progress on remote sensing monitoring of lake water quality parameters [J]. Environmental Science, 2023, 44(3): 1228-1243. [
|
| [7] |
李苗, 臧淑英, 吴长山. 基于TM影像的克钦湖叶绿素a浓度反演 [J]. 农业环境科学学报, 2012, 31(12): 2473-2479.]
Li M, Zang S Y, Wu C S. Inversion of Chlorophyll-a Concentration Based on TM Remote Sensing Image in Keqin Lake [J]. Journal of Agro-Environment Science, 2012, 31(12): 2473-2479. [
|
| [8] |
封红娥, 李家国, 朱云芳, 等. GF-1与Landsat8水体叶绿素a浓度协同反演——以太湖为例 [J]. 国土资源遥感, 2019, 31(4): 182-189.]
Feng H E, Li J G, Zhu Y F, et al. Synergistic inversion method of chlorophyll a concentration in GF-1 and Landsat8 imagery: A case study of the Taihu Lake [J]. Remote Sensing for Land and Resources, 2019, 31(4): 182-189. [
|
| [9] |
谢恩弘, 吴骏恩, 杨昆. 基于Sentinel-2影像的洱海叶绿素a质量浓度反演 [J]. 环境工程学报, 2022, 16(9): 3058-3069.]
Xie E H, Wu J E, Yang K. Mass concentration inversion for chlorophyll a in Erhai lake based on Sentinel-2 [J]. Chinese Journal of Environmental Engineering, 2022, 16(9): 3058-3069. [
|
| [10] |
沈娟, 周治刚, 张彤辉, 等. 基于Sentinel-3A的北部湾海域叶绿素a浓度遥感反演研究 [J]. 遥感技术与应用, 2024, 39(1): 110-119.]
Shen J, Zhou Z G, Zhang T H, et al. Inversion of Beibu Gulf chlorophyll a concentration based on Sentinel-3A Satellite [J]. Remote Sensing Technology and Application, 2024, 39(1): 110-119. [
|
| [11] |
徐鹏飞, 毛峰, 金平斌, 等. 基于GF1_WFV的千岛湖水体叶绿素a浓度时空变化 [J]. 中国环境科学, 2020, 40(10): 4580-4588.]
Xu P F, Mao F, Jin P B, et al. Spatial-temporal variations of chlorophyll-a in Qiandao lake using GF1_WFV data [J]. China Environmental Science, 2020, 40(10): 4580-4588. [
|
| [12] |
吴迪, 于文金, 谢涛. 高分二号卫星数据在粤港澳大湾区水体有机污染监测中的应用 [J]. 热带地理, 2020, 40(4): 675-683.]
Wu D, Yu W J, Xie T. Application of GF-2satellite data for monitoring organic pollution delivered to water bodies in the Guangdong-Hong Kong-Macao greater bay area [J]. Tropical Geography, 2020, 40(4): 675-683. [
|
| [13] |
黄启会, 贺中华, 梁虹, 等. 基于HJ-1A CCD数据的湖泊叶绿素a浓度反演——以贵阳市百花湖为例 [J]. 人民长江, 2019, 50(3): 66-72.]
Huang Q H, He Z H, Liang H, et al. Inversion of chlorophyll-a concentration in baihua lake in Guiyang City based on HJ-1A CCD data [J]. Yangtze River, 2019, 50(3): 66-72. [
|
| [14] |
杜娟, 杨国范, 李佳奇. 基于环境小卫星的凌河叶绿素a浓度定量反演 [J]. 节水灌溉, 2014(9): 50-53.]
Du J, Yang G F, Li J Q. Quantitative retrieval of Chlorophyll-A by remote sensing in Linghe River based on HJ-1B data [J]. Water Saving Irrigation, 2014(9): 50-53. [
|
| [15] |
张永杰, 王卷乐, 冉盈盈, 等. 基于实测光谱分析和MODIS数据鄱阳湖叶绿素a浓度估算 [J]. 长江流域资源与环境, 2013, 22(8): 1081-1089.]
Zhang Y J, Wang J L, Ran Y Y, et al. Estimating chlorophyll-a concentration in Poyang lake using modis based on measured reflectance spectra [J]. Resources and Environment in the Yangtze Basin, 2013, 22(8): 1081-1089. [
|
| [16] |
姚华鑫, 肖潇, 陈品祥, 等. 新一代国产高光谱ZY1-02E卫星在内陆水体水质参数反演中的应用 [J]. 华北水利水电大学学报(自然科学版), 2024, 45(1): 11-20.]
Yao H X, Xiao X, Chen P X, et al. Application of China’s new generation of ZY1-02E hyperspectral satellite in the inversion of water quality parameters in inland waters [J]. Journal of North China University of Water Resources and Electric Power (Natural Science Edition), 2024, 45(1): 11-20. [
|
| [17] |
冯天时, 庞治国, 江威. 基于珠海一号高光谱卫星的巢湖叶绿素a浓度反演 [J]. 光谱学与光谱分析, 2022, 42(8): 2642-2648.]
Feng T S, Pang Z G, Jiang W. Remote sensing retrieval of chlorophyll-a concentration in Lake Chaohu based on Zhuhai-1hyperspectral satellite [J]. Spectroscopy and Spectral Analysis, 2022, 42(8): 2642-2648. [
|
| [18] |
童小华, 谢欢, 仇雁翎, 等. 基于多光谱遥感的水质监测处理方法与分析 [J]. 同济大学学报(自然科学版), 2007, 35(5): 675-680.]
Tong X H, Xie H, Qiu Y L, et al. Multi-spectral remote sensing data based processing method and analysis of water quality monitor [J]. Journal of Tongji University (Natural Science), 2007, 35(5): 675-680. [
|
| [19] |
林剑远, 张长兴. 航空高光谱遥感反演城市河网水质参数 [J]. 遥感信息, 2019, 34(2): 23-29.]
Lin J Y, Zhang C X. Inversion of water quality parameters of urban river network using airborne hyperspectral remote sensing [J]. Remote Sensing Information, 2019, 34(2): 23-29. [
|
| [20] |
Vander Woude A, Ruberg S, Johengen T, et al. Spatial and temporal scales of variability of cyanobacteria harmful algal blooms from NOAA GLERL airborne hyperspectral imagery [J]. Journal of Great Lakes Research, 2019, 45(3): 536-546. doi: 10.1016/j.jglr.2019.02.006
|
| [21] |
Saberioon M, Khosravi V, Brom J, et al. Examining the sensitivity of simulated EnMAP data for estimating chlorophyll-a and total suspended solids in inland waters [J]. Ecological informatics, 2023, 75: 102058. doi: 10.1016/j.ecoinf.2023.102058
|
| [22] |
马启良, 原居林, 张爱华, 等. 基于无人机高光谱技术的水质预测反演系统设计与实现 [J]. 湖州师范学院学报, 2022, 44(2): 56-62.]
Ma Q L, Yuan J L, Zhang A H, et al. Design and implementation of water quality prediction and inversion system based on UAV hyperspectral technology [J]. Journal of Huzhou University, 2022, 44(2): 56-62. [
|
| [23] |
冯翠杰, 方晨琦, 袁亘宇, 等. 基于无人机高光谱和BP神经网络的城市水体污染监测 [J]. 环境工程学报, 2023, 17(12): 3996-4006.] doi: 10.12030/j.cjee.202308120
Feng C J, Fang C Q, Yuan G Y, et al. Water pollution monitoring based on unmanned aerial vehicle(UAV) hyperspectral and BP neural network [J]. Chinese Journal of Environmental Engineering, 2023, 17(12): 3996-4006. [ doi: 10.12030/j.cjee.202308120
|
| [24] |
马启良, 刘梅, 祁亨年, 等. 基于CSA-PLS算法的养殖水体水质快速高光谱预测反演模型研究 [J]. 海洋与湖沼, 2024, 55(2): 375-385.]
Ma Q L, Liu M, Qi H N, et al. Fast hyperspectral prediction and inversion model of aquaculture water quality based on csa-pls Algorithm [J]. Oceanologia et Limnologia Sinica, 2024, 55(2): 375-385. [
|
| [25] |
Rundquist D C, Han L, Schalles J F, et al. Remote measurement of algal chlorophyll in surface waters: the case for the first derivative of reflectance near 690 nm [J]. Photogrammetric Engineering and Remote Sensing, 1996, 62(2): 195-200.
|
| [26] |
Gordon H R, Clark D K, Mueller J L, et al. Phytoplankton pigments from the Nimbus-7 coastal zone color scanner: comparisons with surface measurements [J]. Science, 1980, 210(4465): 63-66. doi: 10.1126/science.210.4465.63
|
| [27] |
曹红业, 龚涛, 袁成忠, 等. 基于RBF模型的太湖北部叶绿素a浓度定量遥感反演 [J]. 环境工程学报, 2016, 10(11): 6499-6504.]
Cao H Y, Gong T, Yuan C Z, et al. Quantitative retrieval of chlorophyll-a concentration in northern part of Lake Taihu based on RBF model [J]. Chinese Journal of Environmental Engineering, 2016, 10(11): 6499-6504. [
|
| [28] |
朱云芳, 朱利, 李家国, 等. 基于GF-1 WFV影像和BP神经网络的太湖叶绿素a反演 [J]. 环境科学学报, 2017, 37(1): 130-137.]
Zhu Y F, Zhu L, Li J G, et al. The study of inversion of chlorophyll a in Taihu based on GF-1 WFV image and BP neural network [J]. Acta Scientiae Circumstantiae, 2017, 37(1): 130-137. [
|
| [29] |
张雪, 郑小慎. 基于BP神经网络渤海湾表层叶绿素浓度反演方法探讨 [J]. 海洋技术学报, 2018, 37(6): 79-87.]
Zhang X, Zheng X S. Discussion on retrieval method of surface chlorophyll concentration of the Bohai Bay based on BP neural network [J]. Journal of Ocean Technology, 2018, 37(6): 79-87. [
|
| [30] |
Xue J, Shen B. A novel swarm intelligence optimization approach: sparrow search algorithm [J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.
|
| [31] |
程晓钰. 机载高光谱数据处理关键技术研究[D]. 上海: 中国科学院大学(中国科学院上海技术物理研究所), 2019: 15-16.]
Cheng X Y. Research on The Key Technologies of Airborne Hyperspectral Data Processing[D]. Shanghai: Shanghai Institute of Technical Physics, Chinese Academy of Sciences, 2019: 15-16.
|
| [32] |
王春玲, 史锴源, 明星, 等. 基于机器学习的水体化学需氧量高光谱反演模型对比研究 [J]. 光谱学与光谱分析, 2022, 42(8): 2353-2358.]
Wang C L, Shi K Y, Ming X, et al. A comparative study of the COD hyperspectral inversion models in water based on the maching learning [J]. Spectroscopy and Spectral Analysis, 2022, 42(8): 2353-2358. [
|
| [33] |
王彩玲, 王一鸣. 基于高光谱与改进BP神经网络的水体生化需氧量(BOD)估算 [J]. 中国无机分析化学, 2023, 13(9): 986-992.]
Wang C L, Wang Y M. Estimation of biochemical oxygen demand(BOD) content in water bodies based on hyperspectral and improved BP neural network [J]. Chinese Journal of Inorganic Analytical Chemistry, 2023, 13(9): 986-992. [
|
| [34] |
赵侃, 师芸, 牛敏杰, 等. 基于改进麻雀搜索算法优化BP神经网络的PM2.5浓度预测 [J]. 测绘通报, 2022(10): 44-48.]
Zhao K, Shi Y, Niu M J, et al. Prediction of PM2.5 concentration based on optimized BP neural network with improved sparrow search algorithm [J]. Bulletin of Surveying and Mapping, 2022(10): 44-48. [
|
| [35] |
葛渊博, 卢文喜, 白玉堃, 等. 基于SSA-BP与SSA的地下水污染源反演识别 [J]. 中国环境科学, 2022, 42(11): 5179-5187.] doi: 10.3969/j.issn.1000-6923.2022.11.024
Ge Y B, Lu W X, Bai Y K, et al. Inversion and identification of groundwater pollution sources based on SSA-BP and SSA [J]. China Environmental Science, 2022, 42(11): 5179-5187. [ doi: 10.3969/j.issn.1000-6923.2022.11.024
|
| [36] |
陶志勇, 胡启振, 任晓奎. 基于二层分解技术和改进神经网络的河流溶解氧预测研究 [J]. 云南大学学报(自然科学版), 2022, 44(2): 262-270.] doi: 10.7540/j.ynu.20210194
Tao Z Y, Hu Q Z, Ren X K. Prediction of dissolved oxygen in river based on two level decomposition and improved neural network [J]. Journal of Yunnan University (Natural Sciences Edition), 2022, 44(2): 262-270. [ doi: 10.7540/j.ynu.20210194
|
| [37] |
任中杰. 基于SSA-BP-SVM模型的云龙湖水质反演研究 [J]. 南京信息工程大学学报, 2024, 16(2): 279-290.]
Ren Z J. Water quality retrieval of Yunlong Lake based on SSA-BP-SVM model [J]. Journal of Nanjing University of Information Science & Technology, 2024, 16(2): 279-290. [
|
| [38] |
潘鑫, 杨子, 杨英宝, 等. 基于高分六号卫星遥感影像的太湖叶绿素a质量浓度反演 [J]. 河海大学学报(自然科学版), 2021, 49(1): 50-56.]
Pan X, Yang Z, Yang Y B, et al. Mass concentration inversion analysis of chlorophyll a in Taihu Lake based on GF-6satellite data [J]. Journal of Hohai University (Natural Sciences), 2021, 49(1): 50-56. [
|
| [39] |
韦安娜, 田礼乔, 陈晓玲, 等. 基于穷举法的鄱阳湖叶绿素a浓度高光谱反演模型与应用研究——以GF-5卫星AHSI数据为例 [J]. 华中师范大学学报(自然科学版), 2020, 54(3): 447-453.]
Wei A N, Tian L Q, Chen X L, et al. Retrieval and application of chlorophyll-a concentration in the Poyang Lake based on exhaustion method: a case study of Chinese Gaofen-5 Satellite AHSI data [J]. Journal of Central China Normal University (Natural Sciences), 2020, 54(3): 447-453. [
|
| [40] |
黄启会, 贺中华, 梁虹, 等. 基于高光谱数据的百花湖叶绿素a浓度估算 [J]. 环境科学与技术, 2019, 42(1): 134-141.]
Huang Q H, He Z H, Liang H, et al. Estimation of chlorophyll-a concentration in baihua lake water based on hyspectral data [J]. Environmental Science & Technology, 2019, 42(1): 134-141. [
|
| [41] |
李优. 三峡库区回水区叶绿素a浓度遥感反演方法研究[D]. 北京: 中国地质大学(北京), 2017: 28-30.]
Li Y. Remote Sensing Retrieval Model for Chlorophyll-a Concentration of Water in Backwater Area, Three Gorges Reservoir[D]. Beijing: China University of Geosciences (Beijing), 2017: 28-30.
|
| [42] |
王会, 王永前, 李剑锋, 等. 基于无人机多光谱数据的三峡库区支流叶绿素a浓度估算——以小江为例 [J]. 成都信息工程大学学报, 2024, 39(2): 233-239.]
Wang H, Wang Y Q, Li J F, et al. Estimation of chlorophyll a concentration in Three Gorges Reservoir branch based on UAV multispectral data —— a case study of Xiaojiang River [J]. Journal of Chengdu University Of Information Technology, 2024, 39(2): 233-239. [
|
| [43] |
郑丙辉, 张远, 富国, 等. 三峡水库营养状态评价标准研究 [J]. 环境科学学报, 2006, 26(6): 1022-1030.]
Zheng B H, Zhang Y, Fu G, et al. On the assessment standards for nutrition status in the Three Gorge Reservoir [J]. Acta Scientiae Circumstantiae, 2006, 26(6): 1022-1030. [
|
| [44] |
朱冰川, 尤凯, 石浚哲, 等. 基于GOCI数据的太湖叶绿素a浓度反演和蓝藻水华遥感监测 [J]. 环境污染与防治, 2020, 42(8): 1021-1025.]
Zhu B C, You K, Shi J Z, et al. Retrieval of chlorophyll-a and remote sensing monitoring of cyanobacteria blooms in Taihu Lake based on GOCI data [J]. Environmental Pollution & Control, 2020, 42(8): 1021-1025. [
|
| [45] |
黄宇波, 曹光荣, 范向军, 等. 汛期水库调度对小江水华的影响 [J]. 长江科学院院报, 2024, 41(1): 52-58.] doi: 10.11988/ckyyb.20221549
Huang Y B, Cao G R, Fan X J, et al. Influence of reservoir operation in flood season on water bloom of Xiaojiang River [J]. Journal of Changjiang River Scientific Research Institute, 2024, 41(1): 52-58. [ doi: 10.11988/ckyyb.20221549
|
DownLoad: