The barriers for the development of continuous monitoring of Suspended Sediment Concentration (SSC) in channels/rivers include costs and technological gaps but this paper shows that a solution is feasible by: (i) using readily available high-resolution images; (ii) transforming the images into image analytics to form a modelling dataset; and (iii) constructing predictive models by learning inherent correlation between observed SSC values and their image analytics. High-resolution images were taken of water containing a series of SSC values using an exploratory flume. Machine learning is processed by dividing the dataset into training and testing sets and the paper uses the following models: Generalized Linear Machine (GLM) and Distributed Random Forest (DRF). Results show that each model is capable of reliable predictions but the errors at higher SSC are not fully explained by modelling alone. Here we offer sufficient evidence for the feasibility of a continuous SSC monitoring capability in channels before the next phase of the study with the goal of producing practice guidelines.
Prediction models of cation exchange capacity (CEC) in soil management is investigated by using artificial intelligence for a balanced approach between advantageous CEC-rich and negative CEC-deficient soil conditions. The modelling strategy formed here comprises: (1) artificial neural networks based on feedforward multi-layer perceptron (MLP) and their backpropagation using Levenburg-Marquardt (LM) algorithm; (2) FireFly algorithm (FFA) to replace LM; (3) learn the dependency of CEC on soil characteristics (clay, silt, sand, gypsum, organic matter) by both models to produce outputs; and (4) feed these outputs as inputs to support vector machine using the least squares algorithms (SVM-LS) together with observed values as target values. This is referred to as multiple models (MM-SVM) strategy. The results of a study area with 380 soil samples collected from different horizons of 80 soil profiles show that the learning by MM-SVM is considerable and capable of reducing inherent uncertainty with benefits to CEC soil management by reducing uncertainty due to solution methods.
A study of climate change scenarios is presented in this paper by projecting a set of recorded precipitation data into three future periods by statistical downscaling methods by employing LARS-WG using data from 7 synoptic stations. The study area covers the basin of Lake Urmia and its overlaps with two of its surrounding basins owing to the Caspian Sea. The modelling is at two stages: Downscaling comprises: (i) use large-scale GCM models to provide climate variables (predictors); and (ii) downscale them to the local climatic variables for correlating with the observed timeseries (e.g. rainfall) for the period of T0: 1961-2001 -40 years; Projecting comprises the derivation of precipitation values during the time periods of ; T1: 2011-2030), T2: 2046-2065 and T3: 2080-2099 at synoptic stations using three of standard scenarios: A1B, A2 and B1. These values are then used to map the climate zoning, which show: (i) climates at T1 are still similar to T0 and if any difference, precipitation increases; but changes are likely at T2 and T3 periods; (ii) the climate is moving toward a peakier regime at the northern region but drier towards the central region; and (iii) precipitation is likely to decrease in some of the zones. Thus, the results underpin the need for more responsive policymaking and should this not be realised in the next 5 to 10 years, the future seems bleak, as the loss of Lake Urmia and the depletion of aquifers are likely to be permanent, in icting immigration from the region.
Tabriz, as one of the most earthquake-prone cities in the Iran plateau, has experienced enormous earthquakes that have even destroyed the city altogether. Considering this seismological background and the vicinity of Tabriz's northwestern fault, reducing the possible earthquake losses can be highly useful by scrutinizing the strong ground motion resulting from the fault activation. To this end, a stochastic finite-fault ground motion simulation (EXSIM) method was applied as an important means for predicting the ground motion near the epicenter of the earthquake. EXSIM is an open-source stochastic finite-fault simulation algorithm that generates the time-series of the earthquake's ground motion. Based on the findings, the peak horizontal acceleration reached 0.83 g in the northern parts by creating artificial accelerograms and Tabriz's seismic zonation. In comparison, it reduced by 0.48 g by departing from the fault in the city's southern parts. Additionally, providing a seismic zonation map in Tabriz revealed that stopping the construction in the north parts while extending the settlement construction to the south part of the city are considered vital and unavoidable. Also, by applying the magnification and effects of the soil layers above the bedrock, it was further found that the existence of the loose layer with low strength and compaction intensify the application of seismic acceleration on the near-surface structures in the central, west, and southwest parts of the target area.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.