基于深度学习的旧金山湾水质预测

doi:10.13278/j.cnki.jjuese.20190144

摘要/Abstract

摘要： 传统的水质预测模型计算复杂，且在大对流情况下会引发误差，对于大数据时代下智能化的水质预测问题并不适用。本文针对旧金山湾地表水质研究区的数据资料，利用数据分析、统计检验、深度学习时序模型等技术方法对该研究区的水质进行研究，根据主成分信息构建了长短时记忆（LSTM）循环神经网络模型，对研究区的5个地表水质采样站点进行了水质预测。结果表明：长短时记忆循环神经网络模型通过门控制循环和记忆单元结构，有效控制传入模型的输入特征，从而降低模型的复杂度；双层长短时记忆循环神经网络模型较单层长短时记忆循环神经网络模型的预测精度平均提高5.3%。利用LSTM模型可以对旧金山湾地表水质进行有效评价。

关键词: 水质预测, 深度学习, 地表水, 统计检验, 数据分析

Abstract: The traditional water quality prediction model is complicated in calculation and will cause errors in the case of large convection, so it is not applicable to intelligent water quality prediction in the era of big data. Based on the data of San Francisco Bay surface water quality research area, the authors studied the water quality of the research area by using data analysis, statistical testing, deep learning time series models,and other technical methods. Based on the principal component information, a long short term memory(LSTM) circulation neural network model was constructed, and further,the water quality of 5 surface water sampling sites was predicted. The results show that the long short term memory cyclic neural network model can effectively control the loop and memory unit structure through gates and the input characteristics of the incoming model, thereby reducing the complexity of the model. Moreover, the prediction accuracy of the two-layer long and short-term memory cyclic neural network model is 5.3 % higher than that of the single-layer long and short-term memory cyclic neural network model.

Key words: water quality prediction, deep learning, surface water, statistical test, data analysis

中图分类号:

X832

王新民, 张超超. 基于深度学习的旧金山湾水质预测[J]. 吉林大学学报(地球科学版), 2021, 51(1): 222-230.

Wang Xinmin, Zhang Chaochao. Water Quality Prediction of San Francisco Bay Based on Deep Learning[J]. Journal of Jilin University(Earth Science Edition), 2021, 51(1): 222-230.

参考文献

[1] Kazakis N, Mattas C, Pavlou A, et al. Multivariate Statistical Analysis for the Assessment of Groundwater Quality Under Different Hydrogeological Regimes[J]. Environmental Earth Sciences, 2017, 76:1-13.
[2] 张兆吉,费宇红,郭春艳,等.华北平原区域地下水污染评价[J]. 吉林大学学报(地球科学版), 2012,42(5):1456-1461. Zhang Zhaoji, Fei Yuhong, Guo Chunyan, et al. Evaluation of Groundwater Pollution in the North China Plain[J]. Journal of Jilin University(Earth Science Edition), 2012,42(5):1456-1461.
[3] 余文忠, 唐德善, 陆廷春. 熵权属性识别法在地下水水质评价中的应用[J]. 水电能源科学, 2013(7):41-43. Yu Wenzhong, Tang Deshan, Lu Tingchun. Application of Entropy Weight Attribute Recognition Method in Groundwater Quality Evaluation[J]. Hydroelectric Energy Science, 2013(7):41-43.
[4] Hosseini-Moghari S M, Ebrahimi K, Azarnivand A. Groundwater Quality Assessment with Respect to Fuzzy Water Quality Index (FWQI):An Application of Expert Systems in Environmental Monitoring[J]. Environmental Earth Sciences, 2015, 74(10):7229-7238.
[5] Kumar N V, Mathew S, Swaminathan G. Multifactorial Fuzzy Approach for the Assessment of Groundwater Quality[J]. Journal of Water Resource and Protection, 2010, 2(6):597-608.
[6] 虞未江,贾超,狄胜同,等.基于综合权重和改进物元可拓评价模型的地下水水质评价[J].吉林大学学报(地球科学版), 2019, 49(2):539-547. Yu Weijiang, Jia Chao, Di Shengtong, et al. Groundwater Quality Evaluation Based on Comprehensive Weight and Improved Matter Element Extension Evaluation Model[J]. Journal of Jilin University(Earth Science Edition), 2019, 49(2):539-547.
[7] Przydatek G, Kanownik W. Impact of Small Municipal Solid Waste Landfill on Groundwater Quality[J]. Environmental Monitoring and Assessment, 2019, 191(3):169.
[8] 韩彰, 陈健, 李经纬, 等. 改进物元可拓法在水闸工程安全综合评估中的应用[J]. 水力发电, 2015, 41(4):82-85. Han Zhang, Chen Jian, Li Jingwei, et al. Application of Improved Matter Element Extension Method in Comprehensive Safety Assessment of Sluice Engineering[J]. Hydroelectric Power, 2015, 41(4):82-85.
[9] 李巧, 周金龙, 高业新, 等. 新疆北部平原区2003-2011年地下水水质变化特征[J]. 地学前缘, 2014, 21(4):124-134. Li Qiao, Zhou Jinlong, Gao Yexin, et al. Variation Characteristics of Groundwater Quality in the Northern Plain of Xinjiang from 2003 to 2011[J]. Earth Science Frontiers, 2014, 21(4):124-134.
[10] 何振强,方诗标,陈永明,等.钱塘江感潮河段污染物迁移扩散数值分析[J].环境科学学报,2017,37(5):1668-1673. He Zhenqiang, Fang Shibiao, Chen Yongming, et al. Numerical Analysis of Contaminant Migration and Diffusion in the Tidal River Section of Qiantang River[J]. Journal of Environmental Science, 2017,37(5):1668-1673.
[11] 杨佳, 钱会. 时间序列分析在地下水位动态预测中的应用[J]. 水资源与水工程学报, 2015(1):58-62. Yang Jia, Qian Hui. Application of Time Series Analysis in Dynamic Prediction of Groundwater Level[J]. Journal of Water Resources and Water Engineering, 2015(1):58-62.
[12] Najafabadi M M, Villanustre F, Khoshgoftaar T M. Deep Learning Applications and Challenges in Big Data Analytics[J]. Journal of Big Data, 2015, 2(1):1-21.
[13] Hao X, Zhang G, Ma S. Deep Learning[J]. International Journal of Semantic Computing, 2016, 10(3):417-439.
[14] Wu Z Y, El-Maghraby M, Pathak S. Applications of Deep Learning for Smart Water Networks[J]. Procedia Engineering, 2015, 119:479-485.
[15] 姚俊杨, 许继平, 王小艺,等. 基于深度学习的湖库藻类水华预测研究[J]. 计算机与应用化学, 2015, 32(10):112-115. Yao Junyang, Xu Jiping, Wang Xiaoyi, et al. Prediction of Algal Blooms in Lakes Based on Deep Learning[J]. Journal of Computers and Applied Chemistry, 2015, 32(10):112-115.
[16] Solanki A, Agrawal H, Khare K. Predictive Analysis of Water Quality Parameters using Deep Learning[J]. International Journal of Computer Applications, 2015, 125(9):29-34.
[17] 田亚兰. 水质预测的粒计算求解与深度学习方法[D].重庆:重庆邮电大学,2016. Tian Yalan. Granular Calculation and Deep Learning Method for Water Quality Prediction[D]. Chongqing:Chongqing University of Posts and Telecommunications, 2016.
[18] 王功明, 李文静, 乔俊飞. 基于PLSR自适应深度信念网络的出水总磷预测[J]. 化工学报, 2017,68(5):1987-1997. Wang Gongming, Li Wenjing, Qiao Junfei. Prediction of Total Phosphorus in Effluent Based on PLSR Adaptive Depth Belief Network[J]. CIESC Journal, 2017,68(5):1987-1997.
[19] Robusto C C. The Cosine-Haversine Formula[J]. American Mathematical Monthly, 1957, 64(1):38.
[20] Hochreiter S, Schmidhuber J. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8):1735-1780.

相关文章 15

[1]	陈应显, 朱喆, 富颉鹏, 马慧茹. 基于条件生成对抗网络的深部水文地质剖面生成方法[J]. 吉林大学学报(地球科学版), 2026, 56(3): 975-985.
[2]	李海港, 王涛, 杨艳伟, 董学征, 廖利勇, 付晓东, 刘硕磊, 倪雨苗. 基于深度学习的地下管线探地雷达数据反演[J]. 吉林大学学报(地球科学版), 2026, 56(3): 1026-1037.
[3]	刘洪学, 杨化超, 卞和方, 李斌, 李磊, 汪森. 基于深度学习及人机协同的煤矿区地表遥感影像变化图斑智能提取[J]. 吉林大学学报(地球科学版), 2026, 56(3): 1076-1087.
[4]	胡飞跃, 徐昊翔, 邓成坚, 杨舒铎. 基于深度学习模型的岩溶塌陷易发性评价——以广佛肇地区为例[J]. 吉林大学学报(地球科学版), 2026, 56(2): 584-597.
[5]	刘涛, 刘宗堡, 张可佳, 张岩, 张瑞雪, 刘晓文, 徐翠云. 基于深度学习的致密砂岩储层薄片图像生成与识别方法 [J]. 吉林大学学报(地球科学版), 2026, 56(2): 724-738.
[6]	齐娇, 曹思远. 基于先验知识的深度学习表面相关多次波压制方法[J]. 吉林大学学报(地球科学版), 2025, 55(5): 1702-1714.
[7]	闫纲丽, 冯屾, 刘睿男, 黄冠星. 地下水背景值评估研究进展[J]. 吉林大学学报(地球科学版), 2025, 55(5): 1655-1670.
[8]	杨笑天, 谭金林, 鱼昕, 赵俊哲, 刘铭. 基于GAM-YOLOv8的遥感图像舰船目标跟踪[J]. 吉林大学学报(地球科学版), 2025, 55(1): 328-339.
[9]	段磊, 曾经文, 赵显林, 丘锦荣, 刘娜, 陶钧实, 周建利. 珠江三角洲典型水产养殖区浅层地下水碘化物分布、来源及健康风险评估[J]. 吉林大学学报(地球科学版), 2024, 54(5): 1657-1674.
[10]	高康哲, 王凤艳, 刘子维, 王明常. 基于改进U-Net的遥感图像语义分割[J]. 吉林大学学报(地球科学版), 2024, 54(5): 1752-1763.
[11]	王婷婷, 孙振轩, 戴金龙, 姜基露, 赵万春. 松辽盆地中央坳陷区储层岩性智能识别方法 [J]. 吉林大学学报(地球科学版), 2023, 53(5): 1611-1622.
[12]	刘霞, 孙英杰. 基于融合残差注意力机制的卷积神经网络地震信号去噪[J]. 吉林大学学报(地球科学版), 2023, 53(2): 609-.
[13]	张岩, 刘小秋, 李杰, 董宏丽, . 基于时频联合深度学习的地震数据重建[J]. 吉林大学学报(地球科学版), 2023, 53(1): 283-296.
[14]	熊越晗, 刘东燕, 刘东升, 王艳磊, 唐小山. 基于岩样细观图像深度学习的岩性自动分类方法[J]. 吉林大学学报(地球科学版), 2021, 51(5): 1597-1604.
[15]	孙超, 许成杰. 基坑开挖对周边环境的影响[J]. 吉林大学学报(地球科学版), 2019, 49(6): 1698-1705.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed