Articles

Conventional SCADA-based water utility control relies on hydraulic models recalibrated through discrete campaigns spaced months to years apart, leaving controllers to act on models that degrade silently between updates. This paper specifies and evaluates a framework that couples a gradient-calibrated hydraulic digital twin to a hierarchically decomposed reinforcement learning controller, coordinating production, transmission, and distribution decisions through Lagrangian relaxation of inter-tier coupling constraints. A differentiable hydraulic solver updates pipe roughness, demand allocation, and valve loss parameters through exact gradients of the prediction residual within a rolling 24-hour window, while a temporal fusion transformer propagates quantile demand forecasts into a risk-sensitive reward term. Evaluated on a 2,400-node benchmark network against a rule-based SCADA baseline across thirty replicated simulation runs, the framework reduced specific energy consumption from 0.58 to 0.40–0.42 kWh/m³, demand forecast error from 14.7% to 4.0–5.0% MAPE, anomaly detection latency from 4.3 hours to 0.3–0.5 hours, treatment dosing error from ±15% to ±4%, and non-revenue water from 32.1% to 21–22%. Lagrangian decomposition reduced joint action-space cardinality from a multiplicative to an additive function of per-tier size, yielding an approximately two-orders-of-magnitude reduction in effective search space for the tested topology. Parameter identifiability under sensor coverage sparser than the benchmark configuration remains untested and bounds the framework's applicability to deployments matching the assumed instrumentation density.

Working on developing geometric coordinates with a special case - in the interest of human engineering - to fit with the humanities or with the famous psychological tests such as the Herman Brain Dominance Instrument Test, which is abbreviated as HBDI, or the Personal Compass test, which is abbreviated as (P.C).

The deflection of the vertical is an important parameter that combines both physical (astronomic) and geometric (geodetic) quantities. It is critical in such areas as datum transformation, reduction of astronomic observation to the geodetic reference surface, geoid modelling and geophysical prospecting. Although the deflection of the vertical is a physical property of the gravitational field of the earth; which almost all terrestrial survey measurements, with the exception of spatial distances, made on the earth surface are with respect to the Earth’s gravity vector, because a spirit bubble is usually used to align survey instruments. It has been ignored in most geodetic computation and adjustment. This research work is therefore aimed at computing the component of the deflection of the vertical component for part of Rivers State using a geometric method. This method involves the integration of Global Positioning System (GPS) to obtain the geodetic coordinate of points, precisely levelling to obtain the orthometric height of this point located within the study area. By least square using MATLAB program, the estimated deflections of vertical component parameters for the test station SVG/GPS-002 were; -0.0473” and 0.0393” arc seconds for the north-south and east-west components respectively. The associated standard errors of the North-south and East-west components were ±0.0093” and ±0.0060” arc seconds, respectively. The deflection of the vertical was also computed independently from gravimetric models of the earth as: ξ = 0.0204” ±0.0008814”, η = -0.0345” ±0.0014”; ξ =0.0157” ±0.000755”, η = -0.0246” ±0.0012”; ξ = -0.0546±0.0006014, η = -0.0208±0.0006014 for EGM 2008, EGM 1996 and EGM 1984 respectively. The two-tailed hypothesis test reveals that the estimated deflection component is statistically correct at 95% confidence interval. It was observed that the effect of the deflection of the vertical is directly proportional to the distance of the geodetic baseline. Therefore, including the derived component of deflection of the vertical to the ellipsoidal model will yield high observational accuracy since an ellipsoidal model is not tenable due to its far observational error in the determination of high-quality job. It is important to include the determined deflection of the vertical component for Rivers State, Nigeria.