Classification Of Water Bodies Research Articles

Using machine learning for the assessment of ecological status of unmonitored waters in Poland

Advancements in Artificial Intelligence (AI) technology allow for development of new tools for analytics and management which present new opportunities in field of environmental protection. The following study showcases usage of Machine Learning (ML) techniques as a complementary method for water status assessment of water bodies. Since the main goal of Water Framework Directive (WFD) is to improve the quality of water and reach good status in all the water bodies across Europe intensive monitoring program was launched together with water status assessment procedure. Based on requirements of the European Union’s WFD concerning ecological status assessment it is presented how ML can be used for assessment of Polish unmonitored river water bodies. Due to the absence of monitoring data, the foremost challenge lay in securing relevant alternative data which was set to be anthropogenic pressures. The pivotal solution was implementation of ML techniques which enable processing of seemingly unrelated information concerning pressures in the catchment. Decision Tree, Random Forest, KNN, Support Vector Machine, Multinomial Naive Bayes, XGBoost models have been tested and the results indicated most suitable techniques. Study shows highest efficiency of XGBoost and Random Forest algorithms for classification of unmonitored water bodies. The models were compared by their overall accuracy (OA) reaching approximately 93% for binary classification and 72% for comprehensive classification as well as partial class accuracies and the Probability of Misclassification (PoM) parameter. The analyses demonstrates a practical application of AI in assessment of unmonitored water bodies in case of binary classification used for reporting water status objectives of WFD as well as possible usage of full classification for planning and operational uses. OA and PoM are postulated as the best measures of goodness of classification.

Intelligent classification of water bodies with different turbidity levels based on Gaofen-1 multispectral imagery

The turbidity of water is crucial for the health of river and lake ecosystems, necessitating efficient monitoring for effective water management. Existing methods for studying water turbidity's spatial and temporal distribution rely mostly on measured data. There is limited research on the classification of water bodies with different turbidity levels. The main challenge lies in determining the boundaries of liquid water bodies at various turbidity levels, making it challenging to classify them accurately using traditional remote sensing image classification methods. This paper proposes and validates an intelligent turbidity classification method based on deep learning using GaoFen-1 multispectral remote sensing imagery. An adaptive threshold water extraction method based on the Normalized Difference Water Index is proposed to capture water boundaries more accurately to improve the accuracy of extracting nearshore water bodies. A semi-automatic semantic annotation method for water turbidity is introduced to reduce manual labeling costs. The paper applies mode filtering to address edge noise issues and establishes a high-quality training sample dataset. After comparing the accuracy of various neural network models, DeepLab V3+ is selected for intelligent turbidity classification. The results show high accuracy, with mean intersection over union (MIoU), mean F1 score (MF1), and overall accuracy (OA) reaching 94.73%, 97.29%, and 97.54%, respectively. The proposed method and experiments demonstrate the feasibility of intelligent classification of water bodies with different turbidity levels using deep learning networks. This provides a new approach for large-scale and efficient remote sensing water turbidity monitoring.

Unveiling the hidden dynamics of intermittent surface water: A remote sensing framework

Intermittent surface water frequently transitioning between water and land over months and years, plays a crucial and increasingly significant role in both social and ecological systems. However, their vital and dramatic dynamics have mainly remained invisible due to monitoring limitations. We present a new remote sensing framework to capture the long-term monthly dynamics of surface water bodies, applying it to Poyang Lake, the largest freshwater lake in China. This framework employed a random forest classifier on all available Landsat data to identify monthly surface water bodies. Additionally, we developed a Spatial and Temporal Neighborhood Similarity-based Gap Filling method to restore water bodies obscured by clouds and ensure spatial integrity. Furthermore, we introduced an index to quantify the intermittency of surface water bodies on a scale from 0 to 1, allowing for the classification of water bodies into three categories: perennial, wet intermittent, and dry intermittent. Employing this framework, we reconstructed the most complete monthly 30-m surface water dataset for cloudy regions to date, covering April 1986 to September 2023, demonstrating a strong correlation (Spearman's rank correlation coefficient of 0.909) with observed water levels. The results reveal a landscape dominantly composed of intermittent water bodies (91.2%), with a rapidly shrinking trend of perennial water bodies at 1303.58 ha per year. Notably, 162,685 ha (21.9%) of water bodies transitioned toward drier and more intermittent statuses. Dry intermittent water bodies exhibited the most pronounced land-water transitions, with the highest water-to-land (82.5%) and land-to-water (89.9%) proportions among the three categories. By uncovering the hidden dynamics of intermittent surface water, and highlighting its prevalence, expansion, and vulnerability, this framework paves the way for a better understanding of these critical water dynamics across the globe.

Comparison of the Direct Supervised Classification and Segment Mean Shift Classification: A Case Study of Hetauda Sub-Metropolitan City of Nepal

Comparison between Land Use Land Cover (LULC) classification and methods is a common practice to assess their suitability and reliability in specific areas. In the case of Hetauda Sub-Metropolitan City in Nepal, Sentinel-2B satellite imagery was utilized to evaluate the accuracy of LULC classification through both direct supervised classification and segment mean shift classification. Direct supervised classification was conducted in ERDAS Imagine, while segment mean shift classification was performed in ArcGIS to identify six LULC classes: forest, agriculture, built-up area, bare area, grassland, and waterbody. Pre-processing steps such as layer stacking, mosaicking, data extraction, atmospheric and radiometric correction were employed to enhance the imagery. Training samples were chosen via visual interpretation based on local knowledge to train the Maximum Likelihood Classifier (MLC). The results revealed that the segment mean shift method achieved the highest overall accuracy at 90%, whereas direct supervised classification yielded 85%. Furthermore, kappa statistics indicated a strong level of agreement, with segment mean shift scoring the highest at 0.88 and direct supervised classification at 0.81. Individual class accuracies varied, with forest classification being the most reliable at 98% and waterbody classification at 71%. Overall, the segment mean shift method was deemed more accurate and suitable than the pixel-based direct supervised classification for LULC classification in Hetauda Sub-Metropolitan City, Nepal.

Trophic Classification of the South Ural water bodies by multivariate statistics

Trophic Classification of the South Ural water bodies by multivariate statistics

Typology and classification of water quality in an intermittent river in a semi-arid Mediterranean climate.

The typology and classification of rivers are highly relevant concepts in the field of limnology and freshwater ecology. Water body typology systematically categorizes water bodies based on their natural attributes, while water body classification groups them based on specific criteria or purposes for management, regulatory, or administrative reasons. Both concepts play important roles in understanding and managing water resources effectively. This scientific article focuses on the ZAT River in Morocco as a model for studying low-flow and intermittent rivers. The objective is to develop an accurate model for the typology and classification of small, low-flow rivers into homogeneous classes based on natural and anthropogenic factors. The study also investigates the impact of human activities on altering the uniformity and reference nature of the water body. The typology of water bodies is carried out according to the European methodology specified in The European Commission's Water Framework Directive (WFD) in 2000. The classification of water bodies is conducted by assessing their chemical and biological quality using the weighted index (WI), the Iberian Biological Monitoring Working Group (IBMWP) index, and multivariate statistical methods such as principal component analysis (PCA) for confirming water quality assessment. The results indicate the possibility of dividing the basin into four water bodies. Water bodies show homogeneity in terms of chemical quality when human influence is minimal or during periods of high river flow. However, increased human influence and decreased river flows lead to heterogeneity in chemical quality, indicating an unstable state. This study is the first of its kind in arid and semi-arid intermittent rivers, where such an approach could be suggested to determine their typology and classification.

Classification of Water Bodies Using Ensemble of U-Net and Random Forest Algorithm

Water bodies classification using remote sensing and deep learning techniques plays a pivotal role in the effective management of water resources. This study aims to address the challenge of accurate water body detection and classification, which is essential for understanding their distribution and characteristics, ultimately informing water usage and conservation efforts. Current methodologies predominantly rely on Support Vector Machines (SVM) and pixel-based approaches, resulting in suboptimal accuracy. In response, this paper proposes an ensemble model that combines the U-Net neural network and the Random Forest algorithm for enhanced water body detection and classification. The research commences by obtaining high-resolution satellite images with a resolution of 0.5 m. The U-Net model is employed to segment water bodies, and contour analysis is subsequently applied to extract shape features. The Random Forest Classifier is then utilized to classify the segmented water bodies into distinct categories, including rivers, ponds, lakes, canals, and other water bodies. Following the U-Net segmentation, the rasterized segments are converted into vector format. These vector data are leveraged to update Geographic Information System (GIS) maps, contributing to more accurate cartographic representations. The proposed approach is rigorously evaluated using a dataset from urban areas in Kolkata, West Bengal, India. The achieved accuracy rate stands at 67.01%.

Development and prediction of a robust multivariate trophic state index for the classification of lentic water bodies

This study presents a novel parametric-non parametric composite approach for developing Multivarite Trophic State Index (MTSI) for the classification of lentic water bodies (LWB). The newly developed framework involves the use of water quality parameters (WQPs), Principal Component Analysis (PCA) and Non-Parametric Gaussian Kernal Density (NPGKD) estimator. The generic framework is demonstrated for developing MTSI, based on the datasets of 18 LWBs in Kerala, India. The method could capture the hypereutrophic status and Akkulam lake was found to be in this state and three other lakes are in eutrophic state for the 2012–2018 database used in this study. The method of developing MTSI is generic and with discrete threshold values which enable its application to any hydroclimatic region. Subsequently, a novel Machine Learning based framework is proposed for prediction of MTSI considering WQPs as inputs. Four machine learning methods and the linear regression are applied for the prediction of MTSI of LWBs of Kerala, considering six combinations of input datasets of WQPs. The rigorous performance evaluation based on multitude of error, coefficient and graphical measures confirmed the superiority of Random Forest as the best method for the prediction of MTSI, for the chosen database. The combination of nine WQPs involving both physical and chemical parameters is found to be the best for MTSI prediction and machine learning offers flexibility to get comparable performance even with lesser number of input variables.

Using Algal Indices to Assess the Ecological Condition of the Aras River, Northwestern Iran

This work is the first in a series, and its purpose is the comprehensive assessment of the ecological state of the Aras River using biological indicators of water quality by diatoms based on species’ ecological preferences, pollution indices, statistics, and ecological mapping. Samples of diatoms and soft algae and measurements of water quality were analyzed at sixteen sampling sites (between 2020 and 2022) along the Aras River. The impact of anthropological activity on the river was monitored concerning water quality, river health, and ecosystem function. The physical and chemical characteristics of the water were measured. The biological properties of the algal periphyton communities, including species composition, were also measured. Based on the studies conducted in this research, 280 species were identified. The most prosperous species were Diatoma vulgaris, Amphora ovalis, Cocconeis placentula, Rhoicosphenia abbre-viatae, Cymbella helvetica, Brevisira arentii, Navicula tripunctata, Nitzschia linearis, Microcystis botrys, Microcystis aeruginosa, Pseudanabaena limnetica, Scenedesmus obliquus, and Pleurosira laevis (a pollution-resistant and salinity-resistant species first found in aquatic habitats in the Aras River). As a result, the empirical data and algal indices showed the river’s lower reaches to be in poor condition. Exploration of the algal assemblage and water chemistry data using computationally unconstrained ordination techniques such as principal component analysis (PCA) and canonical correspondence analysis (CCA) indicated two strong gradients in the data sets. The results support that water body classification is a function of water chemistry and biological and hydrological characteristics, as it is necessary to include pollutant effects on biota since the nature of the receiving waters influences the river’s water quality.

A novel approach to examining the optimal use of the cooling effect of water bodies in urban planning

As the main source of cooling in a city, water bodies play an important role in regulating the natural environment. However, there is a lack of analysis regarding the most effective methods for enhancing the cooling effect of different types of water bodies, as well as classifying the cooling effects based on parameters that affect the cooling effect. This hinders targeted optimization in urban construction. To address this gap, this study used remote-sensing data to develop a novel approach for classifying water bodies according to their actual cooling effect, and establishing a cooling effect prediction model for water bodies based on parameters that affect the cooling effect using machine learning methods. First, the cooling effect of 35 water samples from downtown Nanjing were classified by utilizing the data-mining method. Then the traditional method of classifying water bodies directly from parameters that affect the cooling effect and the classification prediction model established in this study were used to classify water bodies, respectively. It was found that the proposed classification prediction model constructed by combining unsupervised and supervised learning accurately and effectively determined the cooling effect classification of water bodies. Compared with the traditional classification method, the accuracy of the cooling effect classification by the novel approach can be improved by 1.46 times. Additionally, the study examined the correlation factors affecting the cooling effect of each class of water body and identified the most effective measures for improving the cooling effect of each class. It is noteworthy that for different classes, the most effective measures to exert the cooling effect are different. Starting from the parameters that affect the cooling effect of water bodies, this study offers targeted measures for respective water bodies to optimize their cooling density, range, and efficiency. This research provides a basis for using the cooling effect of water bodies more effectively and guiding urban planning and the construction of waterfronts.

Polarimetric Decomposition and Machine Learning‐Based Classification of L‐ and S‐Band Airborne SAR (LS‐ASAR) Data

AbstractThe polarimetric Synthetic Aperture Radar (SAR) data sets have been widely exploited for land use land cover (LULC) classification due to their sensitivity to the structural and dielectric properties of the imaging target. In this study, the potential of fully polarimetric L‐ and S‐band Airborne SAR (LS‐ASAR) data sets were explored for the machine‐learning‐based classification of Urban, Vegetation, Waterbody, and Open Ground. This work was done by utilizing dual‐frequency L‐ and S‐band airborne data of Santa Barbara, California, USA, acquired under the Airborne SAR (LS ASAR) campaign, a precursor airborne mission to the space‐borne NASA‐ISRO (NISAR) mission. The LS‐ASAR polarimetric information was utilized for LULC classification using the SVM classifier. The roll‐invariant Barnes, and eigenvalue/eigenvector‐based Cloude and H/A/Alpha decomposition were implemented to retrieve the scattering parameters. The backscatter response of classes was studied, and separability analysis was done to reduce the misclassification error between six class pairs‐ Vegetation—Urban, Vegetation—Waterbody, Vegetation—Open Ground, Urban—Waterbody, Urban—Open Ground, and Water—Open Ground. The decomposition models failed to achieve the desirable separability index for all six class pairs; consequently, the classification of Barnes, Cloude, H/A/Alpha decomposition showed misclassification between vegetation‐urban class, and waterbody‐open ground class for both L‐ and S‐band data sets. The effort was made toward improving the classification accuracy by integrating the roll‐invariant and eigenvalue‐eigenvector scattering parameters of the multifrequency L‐ and S‐band data set. This method presented the desirable separability index for all class‐pair; eventually highest classification accuracy was achieved i.e. 93.35% ( = 0.91) by significantly reducing the misclassification error between class pairs.

OC_3S: An optical classification and spectral scoring system for global waters using UV–visible remote sensing reflectance

Classification of water bodies is an effective means of understanding the optical properties of aquatic environments. However, most existing water classification systems are mainly based on the visible domain, and the ultraviolet (UV) wavelength, which has important impacts on the growth of phytoplankton, has received less focus. In this study, we developed a novel water classification and spectral scoring system (denoted OC_3S) using 26,709 global in situ hyperspectral data. These spectral data range from the UV to visible domain (380 nm to 750 nm), covering waters from clear to turbid. OC_3S classified water types into 30 classes, providing detailed information on the inherent optical properties and apparent optical properties of different water classes and quality assurance of remote sensing reflectance (Rrs) spectra for multiple sensor data. The results show that OC_3S can capture high-quality Rrs data with little loss of data volume. For example, the uncertainty of Rrs (443) can be reduced by ∼1.33 % at the cost of 5 % of observations in oligotrophic oceans. In addition, OC_3S performs more stably in turbid water classes compared to the QA system (Wei, J., Lee, Z., & Shang, S., 2016b. A system to measure the data quality of spectral remote‐sensing reflectance of aquatic environments. Journal of Geophysical Research: Oceans, 8189–8207) because the coefficient of variation of OC_3S scores in turbid waters can be reduced by ∼44 % compared to that of QA scores. Moreover, good consistency was observed when OC_3S was applied to multiple current satellite images due to its superior tolerance to potential errors in atmospheric correction and radiometric calibration. Our OC_3S is capable of reducing the uncertainty of satellite products and could be applied to future sensors with UV bands (e.g., PACE).

Derivation of Sustainable Reference Chemical Levels for the Protection of Italian Freshwater Ecosystems

The current environmental quality standards (EQSs) for freshwater ecosystems have been established in relation to the priority substances covered by Directive 2013/39/EU. The procedure for deriving EQSs that rely on the selection of the most sensitive toxicological data, with the application of arbitrary safety factors, is probably unrealistic for the Italian freshwater ecosystem. In this work, a procedure for the evaluation of specific sensitivity of 13 taxonomic groups from bacteria to amphibians and the derivation of protective chemical reference values specifically for the Italian aquatic communities was developed. Toxicological raw data of species belonging to the same taxonomic group spending at least one phase of their life cycle in Italian freshwater ecosystems were downloaded from EnviroTox and USEPA ECOTOX databases, aggregated, and then used as input for the model called Species Sensitivity Distribution in order to estimate the predicted no effect concentrations (PNECs). The comparison of relative sensitivity factors (RFSs) made it possible to identify the amphibians as the most sensitive group toward metals, trace elements, and pesticides, whereas crustacean were identified as the most sensitive group toward towards polycyclic aromatic hydrocarbons (PAHs). PNECs were estimated to cover 62 substances, of which 37 identified by Directive 2013/39/EU, and in most of the cases, the values were higher than EQSs. The PNECs reported in this work should be considered more realistic and tailored for Italian freshwater ecosystems, having significant repercussions in the classification of water bodies and the estimation of environmental impact assessment.

Relationship between Pesticide Standards for Classification of Water Bodies and Ecotoxicity: A Case Study of the Brazilian Directive.

The objective of this study was to evaluate if the maximum values (MVs) for pesticides in surface freshwater included in CONAMA directive 357/2005 are safe for aquatic biota, comparing them with ecotoxicology data published in the literature. The terms "aquatic toxicity", "chronic" "acute", "LC50", "EC50", "NOEL", "NOEC" and the name of each pesticide were used for searches on the research platforms. Data from 534 tests reported in 37 published articles and three ecotoxicological databases were included in this study; 24% of the tests were carried out with producer organisms, 34% with primary consumers and 42% with secondary consumers. Microcrustaceans of the Daphnia genus and the fishes Pimephales promelas and Oncorhynchus mykiss were the organisms most used. Atrazine, alachlor and metolachlor were the most investigated pesticides. Atrazine and alachlor are approved in Brazil, with atrazine ranking fourth among the most used pesticides in the country. The results indicated that of the 27 pesticides included in the standard directive, 17 have a risk quotient (RQ) higher than the level of concern for at least one ecotoxicological parameter and may not protect the aquatic biota. The insecticide malathion, used in various agricultural crops in Brazil, was the one that presented the highest RQs (3125 and 3,125,000 for freshwaters classified as 1/2 and 3, respectively), related to a LC50 (96 h) of 0.000032 µg/L in Chironomus ramosus. The results indicate that CONAMA directive 357/2005 should be updated in line with the current use of pesticides in the country, and the MVs should be re-evaluated so that they do not represent toxicity for the aquatic biota.

Efficient Classification of Satellite Image with Hybrid Approach Using CNN-CA

Today, satellite imagery is being utilized to help repair and restore societal issues caused by habitats for a variety of scientific studies. Water resource search, environmental protection simulations, meteorological analysis, and soil class analysis may all benefit from the satellite images. The categorization algorithms were used generally and the most appropriate strategies are also be used for analyzing the Satellite image. There are several normal classification mechanisms, such as optimum likelihood, parallel piping or minimum distance classification that have presented in some other existing technologies. But the traditional classification algorithm has some disadvantages. Convolutional neural network (CNN) classification based on CA was implemented in this article. Using the gray level Satellite image as the target and CNN image classification by the CA’s selfiteration mechanism and eventually explores the efficacy and viability of the proposed method in long-term satellite remote sensing image water body classification. Our findings indicate that the proposed method not only has rapid convergence speed, reliability but can also efficiently classify satellite remote sensing images with long-term sequence and reasonable applicability. The proposed technique acquires an accuracy of 91% which is maximum than conventional methods.

ELSET: Design of an Ensemble Deep Learning Model for improving satellite image Classification Efficiency via Temporal Analysis

Satellite images with multispectral and panchromatic layers may contain a variety of information about the ROI (region of interests). Each layer displays distinct regional characteristics, allowing researchers to identify unique locations. Numerous machine learning algorithms are capable of identifying crop types, land cover types, soil types, etc. Researchers frequently use deep learning classifiers such as FCNN (Fully Connected Neural Network), RNN (Recurrent Neural Network), Q-learning, etc. as a result of their varying performance, applicability, complexity, and implementation costs. These networks are too general for classifications of application-specific satellite images. This paper proposes an improved deep learning model for real-time region-based satellite image classification in application-specific environments. ELSET captures large-scale temporal datasets using Google Earth Engine and removes outliers from these datasets using application-specific segmentation model filters. Image sets are segmented by an upgraded CNN model including VGGNet 19, GoogLeNet, and ResNet V2. VGGNet 19 outperforms other classification techniques for crop type and crop damage detection, GoogLeNet for land cover and forest cover classification, and ResNet V2 for classification of water bodies and urban areas. Combining these algorithms enables the identification of image layered regions with high precision and moderate complexity. Due to these techniques, the proposed model is capable of crop type recognition accuracy of 98.9%, land type identification accuracy of 95.4%, and water & urban cover area classification accuracy of 96.5%. The proposed model was evaluated at various locations and times with consistent precision. The precision, recall, AUC, and latency of the model were compared to state-of-the-art techniques. The proposed model demonstrated 5%, 8%, and 5.9% greater accuracy, recall, and AUC than current models. Due to increased categorization, the suggested model has significantly more latency than conventional alternatives. This paper provides researchers with strategies for context-specific satellite image classification that reduce this delay without compromising model performance levels.

Accurate mapping of Chinese coastal aquaculture ponds using biophysical parameters based on Sentinel-2 time series images

Aquaculture plays a crucial role in the global food security and nutrition supply, where China accounts for the largest market share. Although there are some studies that focus on large-scale extraction of coastal aquaculture ponds from satellite images, they have often variable accuracies and encounter misclassification due to the similar geometric characteristics of various vivid water bodies. This paper proposes an efficient and novel method that integrates the spatial characteristics and three biophysical parameters (Chlorophyll-a, Trophic State Index, and Floating Algae Index) to map coastal aquaculture ponds at a national scale. These parameters are derived from bio-optical models based on the Google Earth Engine (GEE) cloud computing platform and time series of high-resolution Sentinel-2 images. Our proposed method effectively addresses the misclassification issue between the aquaculture ponds and rivers, lakes, reservoirs, and salt pans and achieves an overall accuracy of 91 % and a Kappa coefficient of 0.83 in the Chinese coastal zone. Our results indicate that the total area of Chinese coastal aquaculture ponds was 1,039,214 ha in 2019, mainly distributed in the Shandong and Guangdong provinces. The highest aquaculture intensity occurs within the 1 km coastal buffer zone, accounting for 22.4 % of the total area. Furthermore, more than half of the Chinese coastal aquaculture ponds are concentrated in the 0–5 km buffer zone. Our method is of general applicability and thus is suitable for large-scale aquaculture ponds mapping projects. Moreover, the biophysical parameters we employ can be considered as new indicators for the classification of various water bodies even with different aquaculture species.

Groundwater as an object of legal relations

The concepts of "groundwater", "underground water body", "water body" are considered. The classification of an underground water body is presented. The normative legal acts in the field of subsoil use and water use, as well as the legislation of foreign countries are analyzed. The comparison of direct groundwater objects with the legislation of foreign countries is carried out. The author's concept of classification of underground water bodies and their concepts is presented.

Rapid expansion of an aquatic invasive species (AIS) in Central-European surface waters; a case study of Achnanthidium delmontii

In this work the rapid expansion of a small-celled (<15 µm) monoraphid aquatic invasive species (AIS) along the Central European lotic systems is reported, using the integrated dataset of two large-scale monitoring programs, as supplemented by additional records. Achnanthidium delmontii Pérès, Le Cohu & Barthès 2012 (ADMO) was discovered in 2007 and formally described in 2012, on the basis of specimens from a French river. ADMO was first detected in the upper sections of River Danube in 2013, and has been detectable since 2013, and from 2015 onwards in Hungary. The abundance and the number of occupied habitat types by the species have gradually increased. In 2019, ADMO was found to be among the most abundant and the most frequent species in the River Danube, with a mean relative abundance of at least 5%, and a frequency of at least 10% in samples. To extend the Danubian dataset, the relative abundances of ADMO from 79 freshwater lotic samples were studied to assess their potential of the species as an indicator organism. Weighted average regression was employed to determine the species’ optima and tolerances for 18 environmental variables. ADMO has a wide ecological range, which serves to confirm its potential invasive behaviour. In the case of the following variables, the values were found to be consistent with previously published data on the requirements of the taxon. Despite ADMO prefers high temperatures (estimated optimum = 21.8 °C), its spread shows a downstream pattern of the main watercourses of Europe. The species was first found abundantly from the upper section of River Danube, then with increasing abundance in the middle section, while remaining rare in the lower section. This distribution demonstrates that the River Danube serves as an important linear route for the species' invasion. The results of the study will help improve the ecological classification of water bodies and inform water protection actions undertaken under the auspices of the Water Framework Directive (WFD).

Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors.

Rapid and accurate extraction of water bodies from high-spatial-resolution remote sensing images is of great value for water resource management, water quality monitoring and natural disaster emergency response. For traditional water body extraction methods, it is difficult to select image texture and features, the shadows of buildings and other ground objects are in the same spectrum as water bodies, the existing deep convolutional neural network is difficult to train, the consumption of computing resources is large, and the methods cannot meet real-time requirements. In this paper, a water body extraction method based on lightweight MobileNetV2 is proposed and applied to multisensor high-resolution remote sensing images, such as GF-2, WorldView-2 and UAV orthoimages. This method was validated in two typical complex geographical scenes: water bodies for farmland irrigation, which have a broken shape and long and narrow area and are surrounded by many buildings in towns and villages; and water bodies in mountainous areas, which have undulating topography, vegetation coverage and mountain shadows all over. The results were compared with those of the support vector machine, random forest and U-Net models and also verified by generalization tests and the influence of spatial resolution changes. First, the results show that the F1-score and Kappa coefficients of the MobileNetV2 model extracting water bodies from three different high-resolution images were 0.75 and 0.72 for GF-2, 0.86 and 0.85 for Worldview-2 and 0.98 and 0.98 for UAV, respectively, which are higher than those of traditional machine learning models and U-Net. Second, the training time, number of parameters and calculation amount of the MobileNetV2 model were much lower than those of the U-Net model, which greatly improves the water body extraction efficiency. Third, in other more complex surface areas, the MobileNetV2 model still maintained relatively high accuracy of water body extraction. Finally, we tested the effects of multisensor models and found that training with lower and higher spatial resolution images combined can be beneficial, but that using just lower resolution imagery is ineffective. This study provides a reference for the efficient automation of water body classification and extraction under complex geographical environment conditions and can be extended to water resource investigation, management and planning.