Data Mining and Deep Learning for Predicting the Displacement of “Step-Like” Landslides

Landslide displacement prediction is one of the unsolved challenges in the field of geological hazards, especially in reservoir areas. Affected by rainfall and cyclic fluctuations in reservoir water levels, a large number of landslide disasters have developed in the Three Gorges Reservoir Area. In this article, the Baishuihe landslide was taken as the research object. Firstly, based on time series theory, the landslide displacement was decomposed into three parts (trend term, periodic term, and random term) by Variational Mode Decomposition (VMD). Next, the landslide was divided into three deformation states according to the deformation rate. A data mining algorithm was introduced for selecting the triggering factors of periodic displacement, and the Fruit Fly Optimization Algorithm–Back Propagation Neural Network (FOA-BPNN) was applied to the training and prediction of periodic and random displacements. The results show that the displacement monitoring curve of the Baishuihe landslide has a “step-like” trend. Using VMD to decompose the displacement of a landslide can indicate the triggering factors, which has clear physical significance. In the proposed model, the R2 values between the measured and predicted displacements of ZG118 and XD01 were 0.977 and 0.978 respectively. Compared with previous studies, the prediction model proposed in this article not only ensures the calculation efficiency but also further improves the accuracy of the prediction results, which could provide guidance for the prediction and prevention of geological disasters.

Impact of Water Level Fluctuations on Landslide Deformation at Longyangxia Reservoir, Qinghai Province, China

The construction of Longyangxia Reservoir has altered the hydrogeological conditions of its banks. Infiltration and erosion caused by the periodic rise and fall of the water level leads to collapse of the reservoir banks and local deformation of the landslide. Due to heterogeneous topographic characteristics across the region, water level also varies between different location. Previous research on the influence of fluctuations in reservoir water level on landslide deformation has focused on single-point monitoring of specific slopes, and single-point water level monitoring data have often been used instead of water level data for the entire reservoir region. In addition, integrated remote sensing methods have seldom been used for regional analysis. In this study, the freely-available Landsat8 OLI and Sentinel-2 data were used to extract the water level of Longyangxia Reservoir using the NDWI method, and Sentinel-1A data were used to obtain landslide deformation time series using SBAS-InSAR technology. Taking the Chana, Chaxi, and Mangla River Estuary landslides (each having different reservoir water level depths) as typical examples, the influence of changes in reservoir water level on the deformation of three wading landslides was analyzed. Our main conclusions are as follows: First, the change in water level is the primary external factor controlling the deformation velocity and trend of landslides in the Longyangxia Reservoir, with falling water levels having the greatest influence. Second, the displacement of the Longyangxia Reservoir landslides lags water level changes by 0 to 62 days. Finally, this study provides a new method applicable other areas without water level monitoring data.

PV Based Automatic Irrigation System

In Because of the lack of rains and scarcity of land reservoir water, proper irrigation methods are critical in the field of agriculture. The continuous extraction of water from the earth is lowering the water level, causing a lot of land to slowly come into the unirrigated zones. Another important reason for this is because of unplanned water use, which wastes a significant amount of water. This automatic plant irrigation system is used for this purpose. Solar energy is used to power the system via photovoltaic cells. As a result, there is no need to rely on erratic commercial power. In this digital age, we demand that everything around us be automated, reducing human effort. Electronic circuits are becoming more prevalent, making life easier and simpler in today's world. Energy and water scarcity are two major issues that everyone is dealing with these days. As a result, energy and water conservation are required. The goal is to create a solar-powered prototype that will automatically irrigate the field. Consider how convenient it will be to be able to focus on your next task while your field is being irrigated automatically and at a low cost. No worries about underirrigation or over-irrigation, water waste or expensive electricity, or your busy schedule. Keywords: Arduino Uno-Soil Moisture Sensor Submersible Water Pump - Single Channel Relay - Solar Panel - LCD Display - Buzzer - IDE

Characterization of Mishrif Formation Reservoir in Amara Oil Field, Southeast Iraq, Using Geophysical Well-logging

Reservoir characterization requires reliable knowledge of certain fundamental properties of the reservoir. These properties can be defined or at least inferred by log measurements, including porosity, resistivity, volume of shale, lithology, water saturation, and permeability of oil or gas. The current research is an estimate of the reservoir characteristics of Mishrif Formation in Amara Oil Field, particularly well AM-1, in south eastern Iraq. Mishrif Formation (Cenomanin-Early Touronin) is considered as the prime reservoir in Amara Oil Field. The Formation is divided into three reservoir units (MA, MB, MC). The unit MB is divided into two secondary units (MB1, MB2) while the unit MC is also divided into two secondary units (MC1, MC2). Using Geoframe software, the available well log images (sonic, density, neutron, gamma ray, spontaneous potential, and resistivity logs) were digitized and updated. Petrophysical properties, such as porosity, saturation of water, saturation of hydrocarbon, etc. were calculated and explained. The total porosity was measured using the density and neutron log, and then corrected to measure the effective porosity by the volume content of clay. Neutron -density cross-plot showed that Mishrif Formation lithology consists predominantly of limestone. The reservoir water resistivity (Rw) values of the Formation were calculated using Pickett-Plot method.

Water Quality and Trophic Status of Koto Panjang Reservoir, Indonesia

Koto Panjang Reservoir is one of the hydroelectric power plants in Indonesia, located in Kampar Regency, Riau Province. This paper aims to determine the water quality and tropic status of the Koto Panjang Reservoir. The research was carried out along the Koto Panjang Reservoir, covering the floating net cages area, inlet, outlet, and the center of the reservoir. Water samples were collected twice a year, February and September 2017. The results showed that the water quality of Koto Panjang reservoir is still within the tolerance range for the aquatic organisms' life, including fish. Based on the TSI analysis, the Koto Panjang Reservoir throphic status was categorized as eutrophic to heavy eutrophic. This study recommends that relocating floating net cages is necessary so that the nutrient load will not only be concentrated in one location. The efficiency of using the feed for floating net cages could minimize the waste.

Zooplankton composition and abundance from Nideban Reservoir, Udgir Dist. Latur

Zooplanktons are the microscope free swimming organisms of aquatic system. There are represented by a wide array of taxonomic groups of which the members belonging to protozoa, Rotifera, Cladocera and Copepoda are most common and often dominate the entire communities. They have many remarkable features which hamper their predation by higher organisms. The members of Zooplankton community are important for their role in trophic dynamics, energy transfer in the aquatic ecosystem. They provide food for fishes in the water bodies and play a major role in the fish production. The zooplankton community was studied by monthly samples taken from Oct. 2018 to Feb. 2019. The reservoir water is used for agriculture and fishery activities.

An investigation of methods for calculating the volume of methane dissolved in reservoir water

Existing gas production technologies limit gas recovery at the level of 85 %. Therefore, it is important to introduce technologies that make it possible to maximize the volume of production and intensify the inflow; for their selection it is important to have a reliable estimate of the residual gas reserves, since with a significant volume of the aquifer of gas fields, the volume of dissolved gas can be up to 10 % of the total reserves of the reservoir, which should be taken into account when designing the application of technologies to increase gas recovery.The main hydrocarbon dissolving in reservoir water is methane. In this regard, it is of interest to study methods that make it possible to determine the volume of hydrocarbon gases dissolved in saline water, which will make it possible to determine the total reserves of such gas. We investigated the existing methods for calculating the amount of methane dissolved in reservoir water, and gave a quantitative assessment of the volume of gas dissolved in water.

Forecasting Reservoir Water Levels Using Deep Neural Networks: A Case Study of Angat Dam in the Philippines

Forecasting reservoir water levels is essential in water supply management, impacting both operations and intervention strategies. This paper examines the short-term and long-term forecasting performance of several statistical and machine learning-based methods for predicting the water levels of the Angat Dam in the Philippines. A total of six forecasting methods are compared: naïve/persistence; seasonal mean; autoregressive integrated moving average (ARIMA); gradient boosting machines (GBM); and two deep neural networks (DNN) using a long short-term memory-based (LSTM) encoder-decoder architecture: a univariate model (DNN-U) and a multivariate model (DNN-M). Daily historical water levels from 2001 to 2021 are used in predicting future water levels. In addition, we include meteorological data (rainfall and the Oceanic Niño Index) and irrigation data as exogenous variables. To evaluate the forecast accuracy of our methods, we use a time series cross-validation approach to establish a more robust estimate of the error statistics. Our results show that our DNN-U model has the best accuracy in the 1-day-ahead scenario with a mean absolute error (MAE) and root mean square error (RMSE) of 0.2 m. In the 30-day-, 90-day-, and 180-day-ahead scenarios, the DNN-M shows the best performance with MAE (RMSE) scores of 2.9 (3.3), 5.1 (6.0), and 6.7 (8.1) meters, respectively. Additionally, we demonstrate that further improvements in performance are possible by scanning over all possible combinations of the exogenous variables and only using a subset of them as features. In summary, we provide a comprehensive framework for evaluating water level forecasting by defining a baseline accuracy, analyzing performance across multiple prediction horizons, using time series cross-validation to assess accuracy and uncertainty, and examining the effects of exogenous variables on forecasting performance. In the process, our work addresses several notable gaps in the methodologies of previous works.

ICESat-2 Reservoir Applications: A case study from the largest man-made reservoir in India

Monitoring inland water levels is crucial for understanding hydrological processes to climate change impact leading to policy implementation. Satellite altimetry has proved to be an excellent technique to precisely measure water levels of rivers, lakes, and other inland water bodies. The ATL13 product of ICESat-2 space-borne LiDAR is solely dedicated to inland water bodies. The water surface heights were derived from ICESat-2's strong beams, and performance was assessed with respect to reservoir gauge observations. Statistical measurements were used to understand the agreement (R2= 0.99, %RMSE=0.08) among the datasets. An R2 value of 0.99 was observed between ICESat-2 derived water level anomaly and the reservoir storage anomaly. This study provides a unique opportunity to utilize the ATL13 data product to study reservoir water level variation and estimate the reservoir's storage. The methodology can also be helpful to understand the reservoir storage variation in a data-sparse region.

Main features of reforming the coasts of Kaniv reservoir

Reservoirs provide an electricity generation, promote the development of water transport, municipal and industrial water supply, irrigation, fisheries, recreation and other economic and social needs. However, calls are increasingly being made to limit the creation of new artificial reservoirs and even to destroy existing ones. The reason for this is the significant and very real negative environmental consequences of their creation and functioning – flooding of large areas of valuable land in river valleys, relocation of large numbers of people to new areas, flooding of low and erosion of high banks of reservoirs, deterioration of river water quality due to stagnation and "blooming” and many others. The aim of this work is to analyze the peculiarities of reforming the shores of the Kaniv Reservoir under the impact of hydrological and morphological processes, measures for the coast protection from erosion, deepening the channel and alluvium of new lands by dredging (mainly in the upper part of the reservoir) are considered. The study of this problem in the reservoirs of the Dnieper cascade, including Kaniv, we started from 1993-1997. Therefore, research methods have changed significantly at different stages. Standard methods of soil science were used to study the impact of the reservoir on the coastal soils, primarily on flooding, waterlogging and soil erosion. Since 2010, more detailed terresrial and water expeditionary routes (land) studies have been started to study the overgrowth of the reservoir with hydrophytic and hygrophytic vegetation with the formation of hydromorphic soils on the islands of the reservoir and its coast. Remote sensing methods of the Earth for analyzing the series of space images Landsat-2, 4-5, 7 and 8 were used to study the temporal and spatial changes of landscapes, as well as geospatial positioning of observation points by GARMIN GPS receiver. The important role of the dams construction and pumping stations to protect the low shores of the reservoir from flooding was noted, which, however, created significant problems in the operation of the facility due to rising electricity prices. Attention is paid to the ecological consequences of the new alluvial lands development within the reservoir water area, in particular to “blooming” and deterioration of water quality, as well as to the limitation of the ability to pass extreme floods and the threat of adjacent territories submergence. The nature of erosion and abrasion of the high right bank was studied with the use of a quadcopter, mainly in the area from the village of Rzhishchiv to the village of Trakhtemiriv. The role of marl clays in weakening the abrasion of shores is emphasized and their vulnerability to destruction is shown. The role and development of ravines on the coast and their participation in the fragmentary formation of hydromorphic landscapes along steep cliffs are noted. On the low left bank there is a reformation of the shores in the area from the village of Kyiliv to the Rzhyshchiv military range, where large areas are set aside for fisheries, hunting and recreational activities, as a result of which the wetlands are reduced. The uncertainty of the problem of pumping the water of the Trubizh River into the reservoir to protect the floodplain lands from submergence is emphasized. It is not recommended to use “Raketa” ships for water transport in this reservoir due to their negative impact on shoreline abrasion.