High-resolution Data Based Groundwater Recharge Estimations of Aynalem Well Field

Due to the ever-increasing demand for water in Aynalem catchment and its surrounding, there has been an increased pressure on the Aynalem well field putting the sustainability of water supply from the aquifer under continuous threat. Thus, it is vital to understand the water balance of the catchment to ensure sustainable utilization of the groundwater resource. This in turn requires proper quantification of the components of water balance among which recharge estimation is the most important. This paper estimates the groundwater recharge of the Aynalem catchment using high-resolution hydro-meteorological data. Daily precipitation and temperature measurement data for years 2001-2018; groundwater level fluctuation records collected at every 30 minutes; and soil and land use maps were used to make recharge estimations. In the groundwater level fluctuation, three boreholes were monitored, but only two were utilized for the analysis because the third was under operation and does not represent the natural hydrologic condition. Thornthwaite soil moisture balance and groundwater level fluctuation methods were applied to determine the groundwater recharge of the Aynalem catchment. Accordingly, the annual rate of groundwater recharge estimated based on the soil-water balance ranges between 7mm/year and 138.5 mm/year with the weighted average value of 89.04 mm/year. The weighted average value is considered to represent the catchment value because the diverse soil and land use/cover types respond differently to allow the precipitation to recharge the groundwater. On the other hand, the groundwater recharge estimated using the groundwater level fluctuation method showed yearly groundwater recharge of 91 to 93 mm/year. The similarity in the groundwater recharge result obtained from both methods strengthens the acceptability of the estimate. It also points out that the previously reported estimate is much lower (36 to 66 mm/year).

Potential Use of Treated Wastewater as Groundwater Recharge Using GIS Techniques and Modeling Tools in Dhuleil-Halabat Well-Field/Jordan

Due to limited rainfall and precipitations, different developing countries depend on groundwater (G.W.) resources to challenge water scarcity. This practice of continuous and excessive G.W. pumping has led to severe water shortages and deteriorated water quality in different countries. Recharging of treated wastewater (TWW) into G.W. provides a critical solution for solving water scarcity, extending the well's service life, and maintaining the G.W. supply. However, effective injection practice requires accurate tools and methods to determine the best location for groundwater recharge (GWRC). This work offers a new tool based on GIS–Multi-Criteria Analysis to identify the potential site and locations for GWRC with TWW. The developed methodology was applied to one of the most used well-field areas in Jordan (Dhuleil-Halabat). The G.W. flow for the B-B2/A7 formation system in the area of study was simulated using Processing Modflow (version 8.0). The analysis combined six thematic maps produced following the environmental, technical, and economic criteria to draw conclusions and recommendations. Both steady and transient conditions were used to predict the future changes that might occur under different stresses and after continuous GWR. The study evaluated three possible scenarios of artificial GWRC to evaluate the process efficiency and determine the effect on the water table level. The results revealed that only 0.05% (0.14 Km2) of the total surface area of 450 Km2 is suitable for GWRC. A GWRC with TWW at a rate of 3.65 Mm3/year (MCMY) would provide a good G.W. table recovery to 39.68 m in the year 2025, maintain a steady-state water table ≥ of 50.77 m for up to six years, and secure water supply for future generations. The proposed methodology can be used as a useful tool that can be applied to regulate the GWRC practice worldwide.

A Recurrent Neural Network–Based Proxy Model for Well-Control Optimization with Nonlinear Output Constraints

Summary In well-control optimization problems, the goal is to determine the time-varying well settings that maximize an objective function, which is often the net present value (NPV). Various proxy models have been developed to predict NPV for a set of inputs such as time-varying well bottomhole pressures (BHPs). However, when nonlinear output constraints (e.g., maximum well/field water production rate or minimum well/field oil rate) are specified, the problem is more challenging because well rates as a function of time are required. In this work, we develop a recurrent neural network (RNN)–based proxy model to treat constrained production optimization problems. The network developed here accepts sequences of BHPs as inputs and predicts sequences of oil and water rates for each well. A long-short-term memory (LSTM) cell, which is capable of learning long-term dependencies, is used. The RNN is trained using well-rate results from 256 full-order simulation runs that involve different injection and production-well BHP schedules. After detailed validation against full-order simulation results, the RNN-based proxy is used for 2D and 3D production optimization problems. Optimizations are performed using a particle swarm optimization (PSO) algorithm with a filter-basednonlinear-constraint treatment. The trained proxy is extremely fast, although optimizations that apply the RNN-based proxy at all iterations are found to be suboptimal relative to full simulation-based (standard) optimization. Through use of a few additional simulation-based PSO iterations after proxy-based optimization, we achieve NPVs comparable with those from simulation-based optimization but with speedups of 10 or more (relative to performing five simulation-based optimization runs). It is important to note that because the RNN-based proxy provides full well-rate time sequences, optimization constraint types or limits, as well as economic parameters, can be varied without retraining.

Applications of a Novel Lost Circulation Additive

Lost circulation is a complicated situation in the drilling operation, wasting a lot of time and mud during processing. A serious lost circulation can cause hazards, such as sticking, blowout and collapse of well. There are some problems in conventional plugging technology, such as particle size of plugging material does not match crack width, slip of the blocking zone, and weak adhesion of lost circulation additive to the rock, which restricts the success rate of lost circulation operation. Regular and elastic polyhedron structure material compounds elastic variable network plugging material and rigid plugging materials to form a loss circulation materials (LCM)plugging mixture for different leakage speed and crack width affected by stress. Through plugging and HTHP sand bed experiment loss circulation materials(LCM) and amount of gel were optimized and improved. Through indoor simulation about leakage process of different leakage speed and different crack sizes, the on-site construction formula suitable for wells under different temperature is formed and determined. Scanning electron microscope shows the plugging gel has a variable network structure. By changing the ratio of elastic plugging material, rigid plugging material and gel, a LCM plugging formula for high temperature and high pressure formations can be formed to meet the pressure requirement of 7.5MPa. Leakage simulation formed on-site plan under different leakage rate to adapt to 180°C. The novel CPM material has been well-field tested and used for HPHT reservoirs. When the rate of leakage less than 30 m3/h and 30-60 m3/h, success rate of single plugging is more than 95% and rate of leakage greater than 60 m3/h success rate of single plugging beyond 80%. Leakage loss time is more than 80% shorter than conventional plugging techniques.

USING ARTIFICIAL INTELLIGENCE METHODS TO PREVENT COMPLICATIONS IN WELL CONSTRUCTION

The article discusses the use of automated systems for preventing emergency situa-tions in the process of well construction using artificial intelligence methods to increase the productive time of well construction by reducing the loss of working time to eliminate compli-cations. Key words: problems and complications during drilling, emissions, gas and oil water showings, stuck, artificial neural networks, digitalization, drilling, well, field, oil and gas blockchain, artificial intelligence, machine learning methods, geological and technological research, neural network model, oil and gas construction wells, identification and forecasting of complications, prevention of emergency situations.