基于WorldView-2数据的西沙群岛遥感水深反演——以赵述岛和南岛为例

利用World View-2卫星数据,对西沙群岛的赵述岛和南岛开展了水深反演。以赵述岛为实验区,分析水深与各波段及波段组合的相关性,将水深相关性最大的海岸波段与绿光波段组合作为水深反演因子,建立多种回归拟合模型;将反演结果与实测水深误差对比,确定最佳拟合方式;最后,将该模型应用到南岛,反演其水深等值线图,并将其与南岛实测水深点相较。结果表明,南岛整体水深反演均方根误差在1.25 m以内。     

基于支持向量机和BP神经网络的水深反演研究

根据高空间分辨率Quickbird遥感影像反射率和实测水深之间的相关性,选取相关性较高的反演因子b1/b2、b1/b3和b2/b3建立单因子模型、双因子模型、多因子模型和BP神经网络模型,并对甘泉岛附近20m内的水深进行反演。同时,利用最佳指数因子(OIF)和支持向量机(SVM)对甘泉岛研究区域基于水深颜色分成两类,将分类结果分别提取建立BP神经网络模型并进行水深反演。通过对反演结果对比发现:遥感影像分类前,线性回归模型中多因子线性模型反演精度最高,但比BP神经网络模型稍差。遥感影像分类后,浅海水域BP神经网络模型的反演精度要比分类前的各模型反演精度低,但是,深海区域BP神经网络模型的反演精度最高。     

四种遥感浅海水深反演算法的比较

详细介绍了单波段线性回归模型、两波段比值线性回归模型、多波段组合线性回归模型、BP神经网络模型等4种光学遥感水深反演算法,然后利用同一地区、同一时期的Worldview-2多光谱遥感影像和实测水深数据,对4种水深反演模型的准确性进行了实验比较。研究表明:多波段组合线性回归模型、BP神经网络模型的水深反演的性能较好,利用多光谱遥感图像数据反演得到的水深值误差较小;而单波段线性回归模型、两波段比值线性回归模型的效果较差。     

基于Worldview3数据的浅海水深反演研究

传统水深测量技术灵活性较差,水深资料更新周期长、时效性差。因此,我们需要找寻一种高效便捷方法提取水深。本文采用Worldview3多光谱高分辨率数据与实测数据相结合,针对不同的海底底质类型,建立统计回归模型(单因子模型和多因子模型),对西沙群岛北岛周边的浅海海域,进行浅海水深反演。通过对研究结果的分析,发现单因子模型和多因子模型相关系数都在0.91以上,标准误差也都在1.27以下,反演数据与实测数据偏差较小。且将海底底质分为沙质和草质海底底质类型后建模的精度要高于未对海底底质分类建模的精度。     

CatBoost模型在水深反演中的应用

在多光谱遥感水深反演研究中,由于影响反演精度的因素较多,传统的水深反演模型具有一定局限性。机器学习算法在解决非线性高复杂问题上较有优势,将其应用在某些特定区域水深反演可提高反演精度。本文利用Sentinel-2多光谱遥感影像和LiDAR测深数据,以瓦胡岛为研究区域,构建CatBoost水深反演模型,与传统水深反演模型及Boosting中的XGBoost和LightGBM模型的反演精度进行比较。试验结果表明,经过参数优化后的CatBoost水深反演模型的决定系数、均方根误差、平均绝对误差和平均相对误差分别为96.19%、1.09 m、0.77 m和9.61%,准确性最高,效果更佳。     

海底底质分类支持下的WorldView-3多光谱影像浅海海域水深反演

近几十年来,基于遥感影像进行水深反演一直是国内外学者研究的热点。本文使用WorldView-3高分辨率卫星影像,结合卫星测高数据,以中国海南岛附近的蜈支洲岛及其附近海域为主要研究区域,在进行数据预处理、底质分类之后,分别通过多元线性回归模型、Stumpf对数比值模型和BP神经网络集中对岛屿周围0～20 m水域的水深进行反演和结果分析。结果证明,对这3种模型而言,在进行底质分类之后精度都会明显提升。其中,BP神经网络反演水深精度最高(均方根误差范围为0.2～0.7 m),多元线性回归模型次之(均方根误差范围为0.3～0.8 m),对数比值模型精度最低(均方根误差范围为0.6～1.1 m)。     

利用GA-NN模型反演声速剖面的众源水深数据声速改正

针对当前众源水深数据后处理过程中缺少高精度的实测声速剖面,导致测深数据质量偏低的现状,提出了一种基于遗传算法优化反向传播神经网络（genetic algorithm-back propagation neural network,GA-NN）模型反演声速剖面的声速改正方法。首先,利用历史声速剖面群进行正交经验函数分析,提取特征向量与重构系数范围;然后,结合海区的历史声速场数据训练GA-NN模型;最后,将海表声速数据输入模型反演声速剖面,并分析不同方法下的声速剖面分别进行声速改正后的水深和位置误差。实验结果表明,在复杂的海底地形下,与现有方法相比,所提方法反演的声速剖面更适用于众源水深数据的声速改正,削弱了声速误差的影响,提高了众源水深数据的处理精度。     

基于GA-MLP的东北地区Tm模型研究

针对常用的经验大气加权平均温度(T_m)模型在我国东北地区普遍精度较低等问题,利用遗传算法优化的多层感知器模型,采用东北地区7个探空站2014—2017年的数据进行模型训练,建立适合我国东北地区的T_m模型。依据2018年的数据进行预测分析,实验结果表明：首先,GA-MLP的T_m模型的预测平均偏差为0.04 K、均方误差为4.06 K和判定系数R²=0.920,各项精度评估指标较常用的GPT2w、单/多因子线性、非线性T_m和MLP模型均为最优,模型性能更好,拟合度更高;其次,在GPS反演大气可降水量中,较常用的单因子线性和GPT2w模型,GA-MLP的T_m模型在长春站的反演精度最高,均方误差精度提升1.1%和4.9%,平均偏差精度提升2.5%和13.2%,证明GA-MLP的T_m模型在东北地区反演PWV的适用性。     

非线性模型岛礁礁盘遥感水深反演

针对已有的遥感水深反演方法波段选取难,得不到较好的模型参数的问题,该文在国内外遥感水深反演研究的基础上,对经典的非线性模型进行研究,引入了逐步回归算法对模型进行了改进。以东岛为研究区,基于Worldview-2多光谱影像进行模型验证和精度评价。结果表明:应用改进后模型的反演水深精度大幅提高,水深范围不但适用在10m以浅的水区,在15~30m的区域精度也较高。由此可见改进的模型在保持原模型移植性较好的前提下,模型参数更易解算,反演精度较高,具有一定的适用性。     

两种浅海水深快速反演方法对比研究

针对对数比例变换法和多波段模型法两种操作简便的水深反演方法的优劣进行对比,旨在探讨二者对于大量浅海水深快速反演流程化工作的适用性。基于水深参考数据,随机选取138个样本点分别构建反演模型,并分层随机抽取100个验证点进行精度评价。从模型决定系数R2、反演精度,以及方法鲁棒性和适用性3个方面进行对比分析。结果表明,多波段模型法的决定系数R2(0.912)优于对数比例变换法(0.776);多波段模型法的反演平均绝对误差为1.47m,平均相对误差11.67%,均略低于对数比例变换法(1.45m,11.49%),但后者在小于1m的水深范围内的反演结果存在大范围错误,精度明显低于前者;多波段模型法可通过对回归方程和回归系数的显著性检验而不断优化,鲁棒性和适用性亦明显优于对数比例变换法。因此,本研究认为多波段模型法更适用于大量浅海水深快速反演流程化工作。     

单波束测深数据的插值精度分析

基于误差传播定律,对稀疏的离散水深点内插值进行了精度分析,建立了单波束水深内插值中误差表达的数学模型,利用我国南方某海岸带的3个试验区的进行了试验。试验结果表明,反距离加权法、Shepard法和线性插值三角网法,辅以自适应搜索半径法,内插水深值粗差比例普遍低于5%,质量与效率上为较优的插值模型;内插值精度与数据源精度有关,但与数据源密度关系不大;在给定深度测量极限误差情况下,建议在制定有关数字水深模型标准时,对水深在20 m以内的格网点水深值极限误差可设置为0.4 m。     

二次CUBE滤波算法及在边坡乱石区测深数据处理中的应用

针对传统CUBE（combined uncertainty bathymetry estimation）算法在水下边坡乱石区多波束测深数据滤波中表现出的水深估计不准确、地形特征模糊和粗差剔除能力不足等问题,基于乱石区测深数据特点,提出二次CUBE滤波算法,给出了位置和水深同步估计的思想和方法、顾及地形梯度的平面和水深不确定度传递模型、参考水深的多重估计和优选新算法,以及顾及地形梯度的二次水深估计模型,综合实现了乱石区水深的准确估计和粗差的自动准确检测。试验表明,本文给出的方法实现了粗差的自动准确剔除,提高了传统CUBE算法水深估值的精度,算法效率和抗差性更强,形成的地形特征更加准确。     

多波束换能器吃水误差在分层计算的影响分析

针对传统多波束测深系统中对于换能器吃水改正中,存在误差影响下的声速剖面运用不当,并且未考虑声速分层影响,使得最终水深计算精度不高的问题。该文提出对多波束换能器吃水误差在水深分层计算中的影响进行探究,利用声速分层的计算方式结合吃水误差建立水深计算模型,设定不同吃水改正误差,得到观测偏差与吃水误差间的关系曲线并进行分析。实验表明:实际观测与理论观测深度的差值,受吃水误差的影响,增大速率随着吃水误差的增加会越来越快。     

城市复杂排水管线点埋深的测量精度分析

通过对某市排水设施普查数据进行分析研究,得出当井底状况复杂时,《城市地下管线探测规程》对明显管线点埋深的测量精度要求已很难满足。数据分析显示,当井底状况较为复杂时(少量淤泥或积水)且管线点埋深在3m以下,排水管线点埋深的测量中误差的允许值建议取±10cm;埋深在3m以上时,排水管线点埋深的测量中误差允许值建议取±1/30 H(H为管线点的埋深);当井底状况极为复杂(淤泥较多、积水严重或水流湍急)时,排水管线点埋深测量限差建议按隐蔽管线点处理,建议取值为0.15 H。     

Satellite mapping of Baltic Sea Secchi depth with multiple regression models

Secchi depth is a measure of water transparency. In the Baltic Sea region, Secchi depth maps are used to assess eutrophication and as input for habitat models. Due to their spatial and temporal coverage, satellite data would be the most suitable data source for such maps. But the Baltic Sea’s optical properties are so different from the open ocean that globally calibrated standard models suffer from large errors. Regional predictive models that take the Baltic Sea’s special optical properties into account are thus needed. This paper tests how accurately generalized linear models (GLMs) and generalized additive models (GAMs) with MODIS/Aqua and auxiliary data as inputs can predict Secchi depth at a regional scale. It uses cross-validation to test the prediction accuracy of hundreds of GAMs and GLMs with up to 5 input variables. A GAM with 3 input variables (chlorophyll a, remote sensing reflectance at 678 nm, and long-term mean salinity) made the most accurate predictions. Tested against field observations not used for model selection and calibration, the best model’s mean absolute error (MAE) for daily predictions was 1.07 m (22%), more than 50% lower than for other publicly available Baltic Sea Secchi depth maps. The MAE for predicting monthly averages was 0.86 m (15%). Thus, the proposed model selection process was able to find a regional model with good prediction accuracy. It could be useful to find predictive models for environmental variables other than Secchi depth, using data from other satellite sensors, and for other regions where non-standard remote sensing models are needed for prediction and mapping. Annual and monthly mean Secchi depth maps for 2003–2012 come with this paper as Supplementary materials.     

Bathymetric mapping over coastal Andhra Pradesh using landsat Mss data

Satellite imagery can be used to map shallow water depth using techniques which utilize only a few selected depth sounding points as input. For the present work three different models were considered for water depth estimation, which relate different parameters with the water depth. The Landsat-4 MSS data of the sounding points were used for calculation of model parameters. Goodness of fit of the above models was tested using statistical tests, which showed that the exponential relation between water body radiance and water depth gives best fit for shallow water bathymetry. Contour map of water depths over the coastal region of Andhra Pradesh near Machlipattnam have been drawn with the help of the above models using remotely sensed data of the area.     

Bathymetry retrieval from optical images with spatially distributed support vector machines

This paper presents a spatially distributed support vector machine (SVM) system for estimating shallow water bathymetry from optical satellite images. Unlike the traditional global models that make predictions from a unified global model for the entire study area, our system uses locally trained SVMs and spatially weighted votes to make predictions. By using IKONOS-2 multi-spectral image and airborne bathymetric LiDAR water depth samples, we developed a spatially distributed SVM system for bathymetry estimates. The distributed model outperformed the global SVM model in predicting bathymetry from optical satellite images, and it worked well at the scenarios with a low number of training data samples. The experiments showed the localized model reduced the bathymetry estimation error by 60% from RMSE of 1.23 m to 0.48 m. Different from the traditional global model that underestimates water depth near shore and overestimates water depth offshore, the spatially distributed SVM system did not produce regional prediction bias and its prediction residual exhibited a random pattern. Our model worked well even if the sample density was much lower: The model trained with 10% of the samples was still able to obtain similar prediction accuracy as the global SVM model with the full training set.     

Evaluation of optical remote sensing-based shallow water bathymetry for recursive mapping

Water depth estimation using optical remote sensing offers a reliable and efficient means of mapping coastal zones. Here, we aim to find a suitable model for fast and practical bathymetry of an estuary using Indian Remote Sensing Satellite (IRS) Linear Imaging Self Scanning Sensor (LISS-3) images. The study examines three different models; (1) least square regression model, (2) spectral band-ratio method and (3) multi-tidal bathymetry model. The findings are supported with in situ observed depth values and statistical estimates. Although the least square regression model has provided best results with root mean square error (RMSE) of 0.4 m, it requires a large number of observed data points for absolute depth estimation. Spectral band-ratio and multi-tidal model provides results with RMSEs 2.1 and 0.9 m, respectively. The present investigation demonstrates that multi-date imagery exploitation at disparate tide levels is the best estimation technique for recursive shallow water bathymetry where in situ observation is not possible.