Statistical downscaling of precipitation using machine learning techniques

Thank you for downloading control and optimization methods for electric smart grids. As you may know, people have search numerous times for their favorite books like this control and optimization methods for electric smart grids, but end up in infectious downloads. Rather than enjoying a good book with a cup of tea in the afternoon, instead they cope with some infectious virus inside their laptop.

Control And Optimization Methods For Electric Smart Grids

Konservasi Tanah dan Air Di Indonesia

洪水追跡法(Flood routing)

\n Climate change is a global issue posing threats to the human population and water systems. As Malaysia experiences a tropical climate with intense rainfall occurring throughout the year, accurate rainfall simulations are particularly important to provide information for climate change assessment and hydrological modelling. An artificial intelligence-based hybrid model, the bootstrap aggregated classification tree–artificial neural network (BACT-ANN) model, was proposed for simulating rainfall occurrences and amounts over the Langat River Basin, Malaysia. The performance of this proposed BACT-ANN model was evaluated and compared with the stochastic non-homogeneous hidden Markov model (NHMM). The observed daily rainfall series for the years 1975–2012 at four rainfall stations have been selected. It was found that the BACT-ANN model performed better however, with slight underproductions of the wet spell lengths. The BACT-ANN model scored better for the probability of detection (POD), false alarm rate (FAR) and the Heidke skill score (HSS). The NHMM model tended to overpredict the rainfall occurrence while being less capable with the statistical measures such as distribution, equality, variance and statistical correlations of rainfall amount. Overall, the BACT-ANN model was considered the more effective tool for the purpose of simulating the rainfall characteristics in Langat River Basin.

A proposed hybrid rainfall simulation model: bootstrap aggregated classification tree-artificial neural network (BACT-ANN) for the Langat River Basin, Malaysia.

Climate change has significant impacts on changing precipitation patterns causing the variation of the reservoir inflow. Nowadays, Indonesian hydrologist performs reservoir inflow prediction according to the technical guideline of Pd-T-25-2004-A. This technical guideline does not consider the climate variables directly, resulting in significant deviation to the observation results. This research intends to predict the reservoir inflow using the statistical downscaling (SD) of General Circulation Model (GCM) outputs. The GCM outputs are obtained from the National Center for Environmental Prediction/National Center for Atmospheric Research Reanalysis (NCEP/NCAR Reanalysis). A new proposed hybrid SD model named Wavelet Support Vector Machine (WSVM) was utilized. It is a combination of the Multiscale Principal Components Analysis (MSPCA) and nonlinear Support Vector Machine regression. The model was validated at Sutami Reservoir, Indonesia. Training and testing were carried out using data of 1991–2008 and 2008–2012, respectively. The results showed that MSPCA produced better extracting data than PCA. The WSVM generated better reservoir inflow prediction than the one of technical guideline. Moreover, this research also applied WSVM for future reservoir inflow prediction based on GCM ECHAM5 and scenario SRES A1B.

/pdf/reservoir-inflow-prediction-under-gcm-scenario-downscaled-by-2isllctr6j.pdf

Reservoir Inflow Prediction under GCM Scenario Downscaled by Wavelet Transform and Support Vector Machine Hybrid Models

Recently, agricultural production in the Sampean Baru Irrigation area has not shown optimal cropping production. The average percentage of planted areas in the first (November-February), second (March-June), and third (July-October) planting seasons for the upstream area was 93.67%; 98.02%, and 76.76%, and for the downstream area was 83.54%; 80.81%; and 89.36%. This research aims to optimize the water distribution system based on the calculation of water requirements for plants and the availability of channels to obtain the maximum planting area and amount of agricultural production. This optimization method uses a Dynamic Program with three scenarios. This calculation is based on effective rainfall, crop water requirements, and water discharge availability. Percentage of planted area obtained from the calculation in the dry year for the first, second, and third planting seasons respectively were 100%, 100%, and 90.36%. Based on the existing condition, potential profit obtained for a year is Rp. 170.08 billion. After optimization using Dynamic Program, potential profit in the dry year, normal year, and wet year are IDR 213.52 billion, IDR 215.92 billion, and IDR 228.50 billion, respectively.

/pdf/assessment-and-optimization-of-water-division-pattern-in-3t5x9oqb9j.pdf

Assessment and Optimization of Water Division Pattern in Sampean Baru Irrigation Area

Fulfilment of drinking water needs is one of the government programs to support the achievement of the target of Sustainable Development Goals (SDGs). One of the important parameters in the fulfilment of drinking water needs is a good distribution system. The aims of this research are to create a design to analyse the hydraulic model of drinking water distribution. The utilized model involved the EPANET 2.0 software. The utilized data included land elevation, pipe distribution base map, population, and discharge. The results indicated that the existing design has not fulfilled the standards of availability, hydraulics analysis, and calibration. Therefore, there needs to be a redesign that fulfils all parameters. The results of the new design requires a two-stage development process for the new water distribution system, with the first stage to be executed in 2015-2020 and the second stage to be executed in 2020-2025. Hydraulic analysis shows that additional discharge is needed to increase pressure and velocity. Model calibration was performed by comparing simulated data with field data; the result of pressure calibration is 0.928 and the result of discharge calibration is 0.894. These two results indicated that the results of the simulation are highly correlated with the field conditions.

Evaluation of pipe network distribution system using EPANET 2.0 (a case study of the city of Jember)

Geoelectric represents geophysics method frequently used to study subsurface geology structure, even though it can be applied to explore groundwater. The objective of this study is to investigate groundwater potency using Schlumberger configuration. The investigation result shows that the area study have a good groundwater potential indicated by an aquifer having the character of low resistivity at 15,9 Ωm at sounding point 1 (s1). The aquifer potential lies at depth of about 100 – 125 meter. The inversion model result using IPI2WIN, suggests that the subsurface layers model with error level of 5 percent at each sounding point.

/pdf/pendugaan-potensi-air-tanah-dengan-metode-geolistrik-5c7xcw4400.pdf

Pendugaan potensi air tanah dengan metode geolistrik konfigurasi schlumberger di kampus tegal boto universitas jember

Flood disaster is one of the most common disasters in Jember District. One that is often affected is in 10% of the area of Jember District, namely the Tanggul watershed with an area of 345,875 km2. The condition of Tanggul River, with a length of 23.50 km, which tends to narrow and meander can reduce flow especially when the river discharge is enlarged due to rain. If rainfall is above 100 mm on the upstream part of the watershed, then the downstream of the Tanggul River with a length of ± 10.19 km that passes through Paseban Village, Kraton Village, and Kencong Village are often unable to withstand the discharge which will overflow the surrounding area. The history of flood occurences in the Tanggul watershed in the last 25 years had occurred 27 times, including 9 times which resulting in breakdown of the embankment. According to records from the Lumajang Public Works Office, the latest flood event in Tanggul River was occurred on December 22, 2018 with water elevation reaches 3.5 m and a discharge of 749,153 m3. This resulted in a broken embankment with a length of 60 m and a height of 7.2 m from the riverbed. Mitigation efforts such as flood routing to get an overview and information on overtopping points is needed to be done in order to minimize losses. This research aims to simulate flood using integration of the main programs DELFT3D and GIS. The flood routing model is obtained by utilizing a spatial model of analysis in Geographic Information Systems (GIS) to determine critical embankment or overtopping points and hydraulic flow simulation with DELFT3D program. The modeling results are visually compared with the coordinates of the flood events in the field that prepared by the Lumajang Public Works Office. Based on the 1000-year return period, the overtopping point occurs at ± 12.8 km from the downstream, namely Kencong District and ± 11.8 km from the downstream, namely Paseban District. In the end, this model can be used as a framework for the Tanggul watershed flood routing model to look for the effectiveness of various non-technical flood control alternatives such as land conservation and technical such as river normalization.

/pdf/flood-routing-model-using-integration-of-delft3d-and-gis-4e5vfx23qn.pdf

Gusfan Halik

Papers

Reservoir Inflow Prediction under GCM Scenario Downscaled by Wavelet Transform and Support Vector Machine Hybrid Models

Assessment and Optimization of Water Division Pattern in Sampean Baru Irrigation Area

Evaluation of pipe network distribution system using EPANET 2.0 (a case study of the city of Jember)

Pendugaan potensi air tanah dengan metode geolistrik konfigurasi schlumberger di kampus tegal boto universitas jember

Flood routing model using integration of Delft3D and GIS (case study: Tanggul watershed, Jember)