Wavelet decomposition and deep learning of altimetry waveform retracking for Lake Urmia water level survey

Unmanned Aerial Vehicles (UAVs) can be an excellent tool for environmental measurements due to their ability to reach inaccessible places and fast data acquisition over large areas. In particular drones may have a potential application in hydrology, as they can be used to create photogrammetric digital elevation models (DEM) of the terrain allowing to obtain high resolution spatial distribution of water level in the river to be fed into hydrological models. Nevertheless, photogrammetric algorithms generate distortions on the DEM at the water bodies. This is due to light penetration below the water surface and the lack of static characteristic points on water surface that can be distinguished by the photogrammetric algorithm. The correction of these disturbances could be achieved by applying deep learning methods. For this purpose, it is necessary to build a training dataset containing DEMs before and after water surfaces denoising. A method has been developed to prepare such a dataset. It is divided into several stages. In the first step a photogrammetric surveys and geodetic water level measurements are performed. The second one includes generation of DEMs and orthomosaics using photogrammetric software. Finally in the last one the interpolation of the measured water levels is done to obtain a plane of the water surface and apply it to the DEMs to correct the distortion. The resulting dataset was used to train deep learning model based on convolutional neural networks. The proposed method has been validated on observation data representing part of Kocinka river catchment located in the central Poland.This research has been partly supported by the Ministry of Science and Higher Education Project &#8220;Initiative for Excellence &#8211; Research University&#8221; and Ministry of Science and Higher Education subsidy, project no. 16.16.220.842-B02 / 16.16.150.545.

Download Full-text

Climate change or regional human impacts? remote sensing tools, artificial neural networks, and wavelet approaches aim to solve the problem

Hydrology Research ◽

10.2166/nh.2020.112 ◽

2020 ◽

Author(s):

Ehsan Foroumandi ◽

Vahid Nourani ◽

Elnaz Sharghi

Keyword(s):

Remote Sensing ◽

Neural Networks ◽

Time Series ◽

Artificial Neural Networks ◽

Water Level ◽

Positive Trend ◽

Water Level Change ◽

Lake Urmia ◽

Level Change ◽

Artificial Neural

Abstract Lake Urmia, as the largest lake in Iran, has suffered from water-level decline and this problem needs to be investigated accurately. The major reason for the decline is controversial. The current paper aimed to study the hydro-environmental variables over the Lake Urmia basin using remote sensing tools, artificial neural networks, wavelet transforms, and Mann–Kendall trend tests from 1995 to 2019 in order to determine the primary reason of the decline and to find the most important hydrologic periodicities over the basin. The results indicated that for the monthly-, seasonally-, and annually-based time series, the components with 4-month and 16-month, 24- and 48-month, and 2- and 4-year, respectively, are the most dominant periodicities over the basin. The agricultural increase according to the vegetation index and evapotranspiration and their close relationship with the water-level change indicated that human land-use is the main reason for the decline. The increasing agriculture, in the situations that the precipitation has not increased, caused the inflow runoff to the lake to decline and the remaining smaller discharge is not sufficient to stabilize the water level. Temperature time series, also, has experienced a significant positive trend which intensified the water-level change.

Download Full-text

Urban Water Flow and Water Level Prediction Based on Deep Learning

Machine Learning and Knowledge Discovery in Databases - Lecture Notes in Computer Science ◽

10.1007/978-3-319-71273-4_26 ◽

2017 ◽

pp. 317-329 ◽

Cited By ~ 9

Author(s):

Haytham Assem ◽

Salem Ghariba ◽

Gabor Makrai ◽

Paul Johnston ◽

Laurence Gill ◽

...

Keyword(s):

Deep Learning ◽

Water Level ◽

Water Flow ◽

Urban Water ◽

Water Level Prediction

Download Full-text

Climate change or irrigated agriculture – what drives the water level decline of Lake Urmia

Scientific Reports ◽

10.1038/s41598-019-57150-y ◽

2020 ◽

Vol 10 (1) ◽

Cited By ~ 10

Author(s):

Stephan Schulz ◽

Sahand Darehshouri ◽

Elmira Hassanzadeh ◽

Massoud Tajrishy ◽

Christoph Schüth

Keyword(s):

Climate Change ◽

Water Level ◽

Irrigated Agriculture ◽

Lake Urmia ◽

Water Level Decline

Download Full-text

Estimation of shallow groundwater evaporation from dried-up areas of Lake Urmia, Iran

10.5194/egusphere-egu2020-21046 ◽

2020 ◽

Author(s):

Sahand Darehshouri ◽

Nils Michelsen ◽

Christoph Schüth ◽

Stephan Schulz

Keyword(s):

Water Level ◽

Salt Lake ◽

Shallow Groundwater ◽

Irrigated Agriculture ◽

Lake Area ◽

Lake Urmia ◽

Night Time ◽

Undisturbed Soil ◽

Custom Made ◽

Water Level Decline

Lake Urmia, located in the northwest of Iran, had an initial volume of about 19 km3 and a surface area of 5,700 km2 (Alipour, 2006). Once one of the largest hypersaline lakes in the world, this UNESCO Biosphere Reserve site currently shows a remarkable water level decline. About 70% of the lake area (Tourian et al., 2015) and more than 90% of its volume were lost between 2000 and 2014 (Schulz et al., 2020). The lack of a precise water balance of the Lake Urmia catchment is one of the challenges authorities are facing in their efforts to restore the lake to its ecological level. Here, key issues are that lake evaporation rates are mostly assumed and that evaporation of shallow groundwater from dried-up areas (up to 3,000 km2) is often ignored. The objective of this study is to obtain evaporation rate estimates for the dried-up parts of the Urmia lake bed. To this end, we set up a laboratory experiment with undisturbed soil columns collected from dried-up areas of the lake. With the help of a custom-made low-cost environmental chamber, the columns were subject to day- and night-time weather conditions typical for the area. Performed measurements comprise water level logging and monitoring of mass losses from the columns due to evaporation. First experimental results will be presented.&#160;References Alipour, S., 2006. Hydrogeochemistry of seasonal variation of Urmia Salt Lake, Iran. Saline Systems 2, 9. doi:10.1186/1746-1448-2-9Schulz, S., Darehshouri, S., Hassanzadeh, E., Tajrishy, M., Sch&#252;th, C., 2020. Climate change or irrigated agriculture &#8211; what drives the water level decline of Lake Urmia. Sci. Rep. 1&#8211;10. doi:10.1038/s41598-019-57150-yTourian, M.J., Elmi, O., Chen, Q., Devaraju, B., Roohi, S., Sneeuw, N., 2015. A spaceborne multisensor approach to monitor the desiccation of Lake Urmia in Iran. Remote Sens. Environ. 156, 349&#8211;360. doi:10.1016/j.rse.2014.10.006&#160;

Download Full-text

A deep-learning based water-level measurement method from CCTV camera images

Journal of the Japan society of photogrammetry and remote sensing ◽

10.4287/jsprs.58.28 ◽

2019 ◽

Vol 58 (1) ◽

pp. 28-33

Author(s):

Hideaki MAEHARA ◽

Momoyo NAGASE ◽

Michihiro KUCHI ◽

Toshihisa SUZUKI ◽

Kenji TAIRA

Keyword(s):

Deep Learning ◽

Water Level ◽

Measurement Method ◽

Level Measurement ◽

Cctv Camera

Download Full-text

Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera

Applied Sciences ◽

10.3390/app11209691 ◽

2021 ◽

Vol 11 (20) ◽

pp. 9691

Author(s):

Nur Atirah Muhadi ◽

Ahmad Fikri Abdullah ◽

Siti Khairunniza Bejo ◽

Muhammad Razif Mahadi ◽

Ana Mijic

Keyword(s):

Deep Learning ◽

Water Level ◽

River Water ◽

Correlation Coefficient ◽

Rank Order ◽

Measurement Data ◽

Strong Relationship ◽

Semantic Segmentation ◽

Water Levels ◽

Surveillance Systems

The interest in visual-based surveillance systems, especially in natural disaster applications, such as flood detection and monitoring, has increased due to the blooming of surveillance technology. In this work, semantic segmentation based on convolutional neural networks (CNN) was proposed to identify water regions from the surveillance images. This work presented two well-established deep learning algorithms, DeepLabv3+ and SegNet networks, and evaluated their performances using several evaluation metrics. Overall, both networks attained high accuracy when compared to the measurement data but the DeepLabv3+ network performed better than the SegNet network, achieving over 90% for overall accuracy and IoU metrics, and around 80% for boundary F1 score (BF score), respectively. When predicting new images using both trained networks, the results show that both networks successfully distinguished water regions from the background but the outputs from DeepLabv3+ were more accurate than the results from the SegNet network. Therefore, the DeepLabv3+ network was used for practical application using a set of images captured at five consecutive days in the study area. The segmentation result and water level markers extracted from light detection and ranging (LiDAR) data were overlaid to estimate river water levels and observe the water fluctuation. River water levels were predicted based on the elevation from the predefined markers. The proposed water level framework was evaluated according to Spearman’s rank-order correlation coefficient. The correlation coefficient was 0.91, which indicates a strong relationship between the estimated water level and observed water level. Based on these findings, it can be concluded that the proposed approach has high potential as an alternative monitoring system that offers water region information and water level estimation for flood management and related activities.

Download Full-text

Climate change or irrigated agriculture – what drives the water level decline of Lake Urmia?

10.5194/egusphere-egu2020-11448 ◽

2020 ◽

Author(s):

Stephan Schulz ◽

Sahand Darehshouri ◽

Elmira Hassanzadeh ◽

Christoph Schüth

Keyword(s):

Climate Change ◽

Water Level ◽

Climatic Changes ◽

Water Withdrawal ◽

Water Volume ◽

Irrigated Agriculture ◽

Agricultural Water ◽

Lake Urmia ◽

Data Set ◽

Water Level Decline

Lake Urmia is one of the largest hypersaline lakes on earth with a unique biodiversity. Over the past two decades the lake water level declined dramatically, threatening the functionality of the lake&#8217;s ecosystems. There is a controversial debate about the reasons for this decline, with either mismanagement of the water resources, or climatic changes assumed to be the main cause.During this study we gathered an extensive hydro-meteorological data set, information about the reservoirs and the lake bathymetry. This data served for a quantification of the water budget components of Lake Urmia over the last five decades. Interestingly, a comparison of the temporal patterns of the principal natural boundary conditions of streamflow (precipitation and evaporation) with the inflow to the lake revealed that the variability of the inflow can be well explained its natural drivers. With this we can show that variations of Lake Urmia&#8217;s water level during the analyzed period were mainly triggered by climatic changes.However, under the current climatic conditions agricultural water extraction volumes are significant and often exceed the remaining surface water inflow volumes. This rather simple observation shows that something deeper needs to be dug here. Therefore, we performed a parsimonious hindcast experiment and run a set of development scenarios based on the previously developed water balance. This helped us to better quantify the human impact on the development of the water volume of Lake Urmia. We could show that changes in agricultural water withdrawal would have a significant impact on the lake volume and could either stabilize the lake, or lead to its complete collapse (Schulz et al., 2020).&#160;ReferencesSchulz, S., Darehshouri, S., Hassanzadeh, E., Tajrishy, M. and Sch&#252;th, C.: Climate change or irrigated agriculture &#8211; what drives the water level decline of Lake Urmia, Sci. Rep., 10(1), 236, doi:10.1038/s41598-019-57150-y, 2020.

Download Full-text

Drying Lakes: A Review on The Health Conditions and Restoration Strategies

10.5194/egusphere-egu2020-1207 ◽

2020 ◽

Author(s):

Anchita Anchita ◽

Kamshat Tussupova ◽

Peder Hjorth

Keyword(s):

Water Level ◽

Lake Water ◽

Saline Lakes ◽

Saline Lake ◽

Dust Storms ◽

Water Levels ◽

Aral Sea ◽

Water Withdrawal ◽

Local Context ◽

Lake Urmia

Abstract: Decrease of saline lakes, which comprises of 44% of all the available lake water, is a major concern. It additionally brings to desertification process to the region. Thus, various countries have taken different actions in protecting their lake&#8217;s water level. The aim of this paper is to assess different strategies directed to tackle the decreasing saline lake water levels. Lake Urmia and the Aral Sea which split into North Aral and South Aral were among the world's largest saline lakes and now have reduced to 10% of their original size. A thorough review of academic reports, official documents and databases were considered. Although the dry-up of the lake is a natural process, it has been sped up by human interventions in the hydrology cycle. Dust storms (strong winds) in the case of the Aral Sea, transmit the pollutants from dry lake surface which initially accumulated in the lakebed causing severe health issue. Various strategies were implemented to manage the socio-economic conditions caused due to the drying of lakes. The strategy implemented for the North Aral Sea was to restore the lake by reducing the water withdrawal from tributary rivers which leads to increased water level in the sea. The strategy implemented for Lake Urmia was to restore the lake by water transfer activities from neighbouring water sources which until now show no increase in water level. The strategy implemented for the South Aral Sea was to use a dry lakebed to diversify the economy by oil and mineral extraction which shows the adaptation to the environmental conditions with no restoration strategy. As a conclusion, it is found that there is no common best solution for this kind of problem. The best fit depends on the local context and it is strongly path dependent.&#160;Keywords: Drying saline lake; Dust storms; Aral sea; Health impacts; Lake Urmia; Restoration of saline lake; Strategies.

Download Full-text