Improvement of BPANN Based Algorithm for Estimating Water Depth from Satellite Imagery

doi:10.13474/j.cnki.11-2246.2017.0045

Abstract

Abstract:

BPANN algorithm is commonly used for estimating water depth from satellite imagery. In this paper, an improved BPANN algorithm is presented to overcome some disadvantages of BPANN algorithm. Its principle is that particle swarm optimization (PSO) is used to optimize the weights and thresholds of ANN in the process of training. The experiments show that improved BPANN algorithm has faster convergence speed and better generalization ability, it is not sensitive to initial weights and thresholds, and it can make more accurate results than BPANN algorithm.

Key words: estimating water depth from satellite imagery, backpropagation-based artificial neural network algorithm (BPANN algorithm), particle swarm optimization (PSO), improved BPANN algorithm, optimization of initial weights and thresholds

CLC Number:

P237

CAO Bin, QIU Zhenge, ZHU Shulong, CAO Bincai. Improvement of BPANN Based Algorithm for Estimating Water Depth from Satellite Imagery[J]. 测绘通报, 2017, 0(2): 40-44.

References

[1] 王艳姣, 张鹰. 基于BP人工神经网络的水体遥感测深方法研究[J]. 海洋工程, 2005, 23(4):33-38.
[2] ÖZCELIK C, YALCIN A. Remote Sensing of Water Depths in Shallow Waters via Artificial Neural Networks[J]. Estuarine Coastal & Shelf Science, 2010, 89(1):89-96.
[3] LEE K H, MIZUTANI N, FUJII T. Prediction of Wave Breaking on a Gravel Beach by an Artificial Neural Network[J]. Journal of Coastal Research, 2011, 27(27):318-328.
[4] NAGAMANI P V, CHAUHAN P, SANWLANI N, et al. Artificial Neural Network (ANN) Based Inversion of Benthic Substrate Bottom Type and Bathymetry in Optically Shallow Waters-Initial Model Results[J]. Journal of the Indian Society of Remote Sensing, 2012, 40(1):137-143.
[5] 张振兴, 郝燕玲. 卫星遥感多光谱浅海水深反演法[J]. 中国航海, 2012, 35(1):13-18.
[6] GHOlAMALIFARD M, KUTSER T, ESMAILI-SARI A, et al. Remotely Sensed Empirical Modeling of Bathymetry in the Southeastern Caspian Sea[J]. Remote Sensing, 2013, 5(6):2746-2762.
[7] MOHAMED H, MNEGM A, ZAHRAN M, et al. Assessment of Artificial Neural Network for Bathymetry Estimation Using High Resolution Satellite Imagery in Shallow Lakes:Case Study El Burullus Lake[C]//Proceeding of Eighteenth International Water Technology Conference, Iwtc 18 Sharm Elsheikh.[S.l.]:Research Gate,2015.
[8] 樊彦国, 刘金霞. 基于神经网络技术的遥感水深反演模型研究[J]. 海洋测绘, 2015, 35(4):20-23.
[9] 王正, 毛志华, 曾群,等. 基于BP ANN和B算法的黄河口水深遥感比较研究[J]. 华中师范大学学报(自然科学版),2016, 50(1):112-119.
[10] KENNEDY J,EBERHART R. Particle Swarm Optimization[C]//Proceeding of IEEE International Conference on Neural Networks. Perth:[s.n.],1995:1942-1948.
[11] DEVI S, JAGADEV A K, PATNAIK S. Learning an Artificial Neural Network Using Dynamic Particle Swarm Optimization-Backpropagation:Empirical Evaluation and Comparison[J].Journal of Information and Communication Convergence Engineering,2015,13(2):123-131.
[12] CHATTERJEE S, SARKAR S, HORE S, et al. Particle Swarm Optimization Trained Neural Network for Structural Failure Prediction of Multistoried RC Buildings[J].Neural Computing & Applications, 2016:1-12.
[13] 王刚刚, 廖庆, 徐玉蕊,等. 改进型粒子群优化算法的BP神经网络全息图压缩[J]. 吉林大学学报(信息科学版), 2016, 34(1):147-152.
[14] 杨尚波, 卢小平, 李珵,等. 基于混沌粒子群优化神经网络的GPS高程拟合研究[J]. 测绘通报, 2013(9):5-8.
[15] SHI Y, EBERHART R C. Parameter Selection in Particle Swarm Optimization[C]//Proceeding of International Conference on Evolutionary Programming VII.[S.l.]:Springer-Verlag, 1998:591-600.
[16] 刘锦萍, 郁金祥. 基于改进的粒子群算法的多元线性回归模型参数估计[J]. 计算机工程与科学, 2010, 32(4):101-105.
[17] 曹彬才,邱振戈,朱述龙,等. 高分辨率卫星立体双介质浅水水深测量方法[J].测绘学报,2016,45(8):952-963.