Lower RMSE Values Research Articles

Integrated Flood Risk Management Approach Using Mesh Grid Stability and Hydrodynamic Model

Today, inhabitants residing in floodplains face a serious and perpetual threat of flooding. Flooding causes fatalities and considerable property damage in metropolitan areas. Therefore, robust structural measures need to be adopted to eliminate flood catastrophe. Structural measures in the floodplain are the most promising solutions. However, there are cost-associated factors for proposing a flood retention plan. Navsari city (98.36 km2, area extent) of Gujarat was used as a case study to investigate the impact of mesh grid structures (100 m, 90 m, and 50 m) along with structural measures for the preparation of a flood retention plan. The HEC-RAS 2D hydrodynamic model was performed for the Purna River. The output of the model was characterized by four different scenarios: (i) Without weir and levees (WOWL), (ii) With weir (WW), (iii) With levees (WL), and (iv) With weir and levees (WWL). The statistical parameters (R2, RMSE, NSE, inundation time, and inundation area) were determined to evaluate model accuracy. The outcome of the model revealed that a 50 m size mesh grid exhibited more accurate results, yielding high NSE and R2 values (0.982 and 0.9855), a low RMSE value (0.450 m), and a smaller inundation area (114.61 km2). The results further revealed that the WW scenario was the most effective flood retention measure as it delayed the flood water for up to 16 h, and managed the flood with the WOWL case. Moreover, the mean error (WW scenario) estimated from profiles 1 and 2 ranged from (−0.7 to 0.62) and from (−0.1 to 0.02 m), respectively, which were evaluated as very low when compared with other scenarios. The novel scenario-based flood retention plan emphasizing the stability of mesh grid structures using the hydrodynamic model can be applied to any other region around the globe to recommend efficacious structural flood measures for flood decision making systems.

Feasibility of Harris Hawks Optimization in Combination with Fuzzy Inference System Predicting Heating Load Energy Inside Buildings

Heating and cooling systems account for a considerable portion of the energy consumed for domestic reasons in Europe. Burning fossil fuels is the main way to produce this energy, which has a detrimental effect on the environment. It is essential to consider a building’s characteristics when determining how much heating and cooling is necessary. As a result, a study of the related buildings’ characteristics, such as the type of cooling and heating systems required for maintaining appropriate indoor air conditions, can help in the design and construction of energy-efficient buildings. Numerous studies have used machine learning to predict cooling and heating systems based on variables that include relative compactness, orientation, overall height, roof area, wall area, surface area, glazing area, and glazing area distribution. Fuzzy logic, however, is not used in any of these methods. In this article, we study a fuzzy logic approach, i.e., HHO−ANFIS (combination of Harris hawks optimization and adaptive neuro-fuzzy interface system), to predict the heating load in residential buildings and investigate the feasibility of this technique in predicting the heating load. Fuzzy techniques obtain perfect results. The analysis results show that the HHO−ANFIS with a population size of 400, the highest value of R2 (0.98709 and 0.98794), and the lowest value of RMSE (0.08769 and 0.08281) in the training and testing dataset, respectively, can predict the heating load with high accuracy. According to the high value of R2 (98%) and low value of RMSE, HHO−ANFIS can be used in predicting the heating load of residential buildings.

Reaction Kinetics-Based Modeling and Parameter Sensitivity Analysis of Direct Ethanol Fuel Cells

Ethanol is considered an alternative fuel to power fuel cells, especially due to its ease of transport and storage and renewable production on a large scale. However, its use in direct ethanol fuel cells (DEFC) is still limited by incomplete electro-oxidation and slow reaction kinetics. Modeling approaches have focused on investigating different reaction mechanisms, but so far, no formal analysis of model parameter sensitivity has been conducted. This work modeled and identified sensitive parameters for different types of Pt–Sn catalysts previously prepared by our research group that displayed good performance in the 5–15 mW/cm2 range (relative to a performance of 12 mW/cm2 achieved by a commercial ETEK catalyst). Analyses to study the effect of these parameters on coverage fraction distribution, reaction rates and possible correlations were also performed. The model was developed based on Butler–Volmer kinetics and on a reaction mechanism previously reported in the literature. Statistical developments were considered to compute parameter uncertainties for a non-linear system with non-linear restrictions. The model achieved very good fits to experimental data, with low RMSE values between 0.22 × 10−4 and 4.2 × 10−4 A/cm2, while also showing surface coverage fraction distributions in agreement with other experiment-based works from the literature. All catalysts taken into account, the most sensitive parameters were the reaction rate constants associated with the formation of adsorbed CH3CO, and the direct and reverse water dissociative adsorption reactions, respectively. Additional analyses suggested that there is not much correlation between the parameters. The results from this work could contribute to the state-of-the-art DEFC models by providing insights into which variables may be assumed constant or which ones have the greatest impact on the model output, thus helping to reduce the model size and computational time for future broader DEFC models.

Predictive comparison and assessment of ANFIS and ANN, as efficient tools in modeling degradation of total petroleum hydrocarbon (TPH)

Composting is an effective organic waste management practice with a sustainable environmental impact on soil. In most cases, composting materials are agricultural residues constituting a huge environmental challenge. This study investigates the composting biostimulation of total petroleum hydrocarbon (TPH) contaminated soil using organic compost prepared from palm oil mill effluent (CPOME). The performance of CPOME in TPH degradation was evaluated using the first-order kinetic model and CO₂ evolution. The artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) modelling approaches were further employed to optimize the experimental response. The experimental designs for ANFIS and ANN modelling were done using the central composite design (CCD). Statistical parameters such as RMSE, MSE, and MAE were used to evaluate model performance and comparisons. The first-order kinetic model and CO₂ released showed that TPH degradation favours contaminated soil with 40 g/L initial TPH concentration. The first-order kinetic model observed a decrease in the constant degradation rate with increasing TPH concentration. The CO₂ evolution, which measures microbial respiration/activity, also showed a decline in released CO₂ with increasing TPH concentration. Lower values of RMSE, MSE, and MAE were obtained for the ANFIS model compared with the ANN. The R² values between the experimental and model-predicted responses showed that the ANFIS (0.9349) model predictions fitted adequately compared to the ANN (0.8862). Finally, comparison and model performances showed that the ANFIS model prediction capability was considerably better than the ANN. • The compost from palm oil mill effluent proved effective in TPH degradation • ANFIS predicted TPH degradation was better than the ANN predicted • Notable organic materials in the compost includes polysaccharides, nitrogen and lignin

Multi-Step Ahead Probabilistic Forecasting of Daily Streamflow Using Bayesian Deep Learning: A Multiple Case Study

In recent decades, natural calamities such as drought and flood have caused widespread economic and social damage. Climate change and rapid urbanization contribute to the occurrence of natural disasters. In addition, their destructive impact has been altered, posing significant challenges to the efficiency, equity, and sustainability of water resources allocation and management. Uncertainty estimation in hydrology is essential for water resources management. By quantifying the associated uncertainty of reliable hydrological forecasting, an efficient water resources management plan is obtained. Moreover, reliable forecasting provides significant future information to assist risk assessment. Currently, the majority of hydrological forecasts utilize deterministic approaches. Nevertheless, deterministic forecasting models cannot account for the intrinsic uncertainty of forecasted values. Using the Bayesian deep learning approach, this study developed a probabilistic forecasting model that covers the pertinent subproblem of univariate time series models for multi-step ahead daily streamflow forecasting to quantify epistemic and aleatory uncertainty. The new model implements Bayesian sampling in the Long short-term memory (LSTM) neural network by using variational inference to approximate the posterior distribution. The proposed method is verified with three case studies in the USA and three forecasting horizons. LSTM as a point forecasting neural network model and three probabilistic forecasting models, such as LSTM-BNN, BNN, and LSTM with Monte Carlo (MC) dropout (LSTM-MC), were applied for comparison with the proposed model. The results show that the proposed Bayesian long short-term memory (BLSTM) outperforms the other models in terms of forecasting reliability, sharpness, and overall performance. The results reveal that all probabilistic forecasting models outperformed the deterministic model with a lower RMSE value. Furthermore, the uncertainty estimation results show that BLSTM can handle data with higher variation and peak, particularly for long-term multi-step ahead streamflow forecasting, compared to other models.

Fourier transform infrared spectroscopy and chemometrics for chemical property prediction of chemically interesterified lipids with butterfat and vegetable oils during storage

The storage stability of structured lipids has a great importance for food industry and should be defined clearly. The aim of the study is to manufacture structured lipids by chemical interesterification of butterfat with different vegetable oils, to determine some chemical properties of interesterified lipids throughout storage and to predict free fatty acid, peroxide value, malondialdehyde and mono-di-triacylglycerol contents of these lipids by using middle infrared spectroscopy (FT-MIR). Prediction models were constructed by using partial least square (PLS) regression with an external cross-validation. The PLS model for TAG with FT-MIR data showed an excellent predictive potential with higher R2cal=0.98, R2cv=0.99 and lower RMSE values. The model for monoacylglycerol content (MAG) showed a good predictive ability with higher R2cal=0.88, R2cv=0.90 and lower RMSE values. The PLS model constructed with FT-IR spectra for diacylglycerol (DAG) content have good capability of prediction due to higher R2 and lower RMSE values. For the prediction of malondialdehyde (MAD) of interesterified lipids by FT-MIR spectra, regression coefficient of calibration set was found as 0.84. For the prediction of peroxide value (PV) of interesterified lipids with FT-MIR spectra, R2CV=0.76 and RMSEC=1.52 and RMSECV=1.15. Infrared spectroscopy technique could be used for analyzing the chemical changes of fats during storage and also suggests a rapid and non-destructive techniques as good alternatives to the traditional analytical methods.

Simulating potential yield of rainfed soybean in northeast Nigeria

We used the CROPGRO-Soybean model to simulate the production potential of rainfed soybean in northeast Nigeria. Data from ten soybean experiments conducted under optimal conditions in 2016–2018 at Kano and Dambatta in the Sudan savanna (SS) agroecological zone were used to determine the cultivar coefficients and calibrate the model for the varieties TGX 1448–2E and TGX1951–3 F. The model was evaluated with data from four phosphorous response trials conducted at Zaria and Doguwa in the northern Guinea savanna (GS) of Nigeria between 2016 and 2018. Results show that the CROPGRO-Soybean model was able to accurately simulate soybean growth and grain yield with low RMSE and high d-index values. Consequently, the model was used to investigate the rainfed yield potential of the two varieties in 24 sites in northeast Nigeria under different sowing windows using 30-year (1985–2014) weather data. The result shows that soybean can be grown in northeast Nigeria, but yield performance is dependent on location, variety and sowing window. The simulated yield was higher in the SS than in the GS agro-ecozone despite the longer growing period in the later. Low yield was simulated for TGX 1448–2E for most of the sites. The yield of TGX1951–3 F was above a threshold of 1500 kg ha−1 in 5 out of 12 sites in the GS and 7 out of 12 sites in the SS, suggesting that this variety is the most suitable for cultivation in northeast Nigeria. Sowing TGX 1951–3 F can be delayed to July 16 at Gwaskara, Nasarawo Demsa and Tawa in the GS and at Briyel, Lakundum, Jara Dali, Kurbo Gayi, and Mathau in the SS with a low-risk of crop failure. The desired yield will be achieved at Chikala and Puba Vidau with a significantly low risk of crop failure for all sowing windows. The results from this study suggest that the CSM-CROPGRO-Soybean model can be a valuable tool in determining the right variety and sowing window for soybean production in targeted agroecological zones in northeast Nigeria.

Predicting the Compressive Strength of Concrete Containing Fly Ash and Rice Husk Ash Using ANN and GEP Models.

Climate change has become trending news due to its serious impacts on Earth. Initiatives are being taken to lessen the impact of climate change and mitigate it. Among the different initiatives, researchers are aiming to find suitable alternatives for cement. This study is a humble effort to effectively utilize industrial- and agricultural-waste-based pozzolanic materials in concrete to make it economical and environmentally friendly. For this purpose, a ternary blend of binders (i.e., cement, fly ash, and rice husk ash) was employed in concrete. Different variables such as the quantity of different binders, fine and coarse aggregates, water, superplasticizer, and the age of the samples were considered to study their influence on the compressive strength of the ternary blended concrete using gene expression programming (GEP) and artificial neural networking (ANN). The performance of these two models was evaluated using R2, RMSE, and a comparison of regression slopes. It was observed that the GEP model with 100 chromosomes, a head size of 10, and five genes resulted in an optimum GEP model, as apparent from its high R2 value of 0.80 and 0.70 in the TR and TS phase, respectively. However, the ANN model performed better than the GEP model, as evident from its higher R2 value of 0.94 and 0.88 in the TR and TS phase, respectively. Similarly, lower values of RMSE and MAE were observed for the ANN model in comparison to the GEP model. The regression slope analysis revealed that the predicted values obtained from the ANN model were in good agreement with the experimental values, as shown by its higher R2 value (0.89) compared with that of the GEP model (R2 = 0.80). Subsequently, parametric analysis of the ANN model revealed that the addition of pozzolanic materials enhanced the compressive strength of the ternary blended concrete samples. Additionally, we observed that the compressive strength of the ternary blended concrete samples increased rapidly within the first 28 days of casting.

Using Rosetta Program in Determining Hydraulic Properties of Three Different Mountainous Textured Soils under Semiarid Conditions of Duhok Iraqi – Kurdistan

This study was carried out in three mountainous different soil textures and two depths. Field measurements of soil texture and bulk density, and laboratory measurements of soil water retention at field capacity (–33 kPa) and permanent wilting point (–1500 kPa), were taken to implement Rosetta. Calculated values of van Genuchten parameters were then compared to measured values. Results showed that Rosetta could be used to obtain values of van Genuchten parameters for a field with different soil textures. The determination coefficient (R2) of It showsthat 50% of determination coefficients(R2) gave more than 0.99 and 30% gave more than 0.98 and the others gave between (0.91-0.97) at applying the (PTFs) at two depths for the studied soils. The Root Mean Square Difference (RMSD) indicated that the lowest values of RMSE were exhibit by all soils (Zawita, Swaratoka and Koradare) and two depths D1 and D2 except D1 of Swaratoka Clay loam soil and at different textures.NSE elevation indicator revealed that the maximum values more than (0.99) were found in Zawita loamy soil and at depth two, D2 whereas the minimum values were noticed in Koradare Silty Loam and at depth two,D2. We conclude that Rosetta is a tool that can be used to calculate van Genuchten parameters the absence of measured values, for the studied soils(Zawita, Swaratoka and Koradare) Rosetta Levels yielded the best results as following: Level 5 gave highest (R2) at applying in (Zawita,D1-Swaratuka and KoradareD2), lowest RMSE and maximum in (Koradare,D2) using the measured input data and thus calculated values ofvan Genuchten parameters can be used as input in simulation models

Prediction of temperature in 2 meters temperature probe survey in Blawan geothermal field using artificial neural network (ANN) method

Research on temperature gradient has been carried out in Blawan geothermal area. This study aims to predict the temperature in the subsurface temperature measurement using a temperature probe with a depth of 2 m in the Blawan geothermal area. Temperature and depth are the two variables being measured. Meanwhile, the resistivity, conductivity, and humidity data were taken from previous studies in the exact area measurements. The prediction determination used modeling with an Artificial Neural Network (ANN) with the back-propagation method. The optimal predictions using an Artificial Neural Network (ANN) were obtained by constructing three input layers, five hidden layers, and two output layers (3-5-2) with a hyperbolic tangent function. Results for temperature prediction with the larger R 2 (1) values and lower MAPE (1.07%), RMSE (0.78), MSE (0.61), and MAD (0.34) values. Moreover, humidity generates a greater R 2 (1) values and lower MAPE (0.34%), RMSE (0.34), MSE (0.18), and MAD (0.29) values. ANN proved very effective in predicting temperature and humidity factors.

Improved Harris Hawks Optimization with Hybrid Deep Learning Based Heating and Cooling Load Prediction on residential buildings

In digital era, energy efficient building remains a hot research topic because of increasing concern regarding their environmental impact and energy consumption. Designing a suitable energy efficient building based on their layout namely overall areas, distribution of the glazing areas, orientation, height, and relative compactness. Such components directly impact the heating load (HL) and cooling load (CL) of residential buildings. A precise predicting of load facilitates effective management of energy consumption and improves the quality of life. Lately, several studies have been implemented to predict the CL and HL. The most significant and challenging parts of predictive are defining the effective input parameter and developing a higher accuracy predictive model. The accuracy of predictive model based on machine learning algorithm must be enhanced by hybrid model. With this motivation, this article introduces an Improved Harris Hawks Optimization with Hybrid Deep Learning Based Heating and Cooling Load Prediction (IHHOHDL-HCLP) model on Residential Buildings. The major aim of the IHHOHDL-HCLP model is to determine the CL and HL to accomplish effective energy utilization. To accomplish this, the IHHOHDL-HCLP primarily pre-processes the raw data in two levels namely min-max normalization and polynomial equation. In addition, the HDL model involves convolutional neural network (CNN) along with long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) for HL and CL prediction process. Finally, the IHHO technique was applied for fine-tuning the hyperparameters related to the DL model. The IHHOHDL-HCLP model has demonstrated maximum prediction results with low RMSE values of 0.00874 and 0.00821, respectively, when applied to HL and CL, respectively. The experimental result analysis of the IHHOHDL-HCLP model demonstrates the better performance of the IHHOHDL-HCLP model over other DL models.

Application of advanced machine learning algorithms for anomaly detection and quantitative prediction in protein A chromatography

Protein A capture chromatography, which forms the core of the mAb purification platform, demands cautious use and maximum resin utilization due to high cost associated with resin. In this paper, we propose an application of advanced machine learning (ML) algorithms to address two most crucial objectives of column integrity breach and yield prediction for resin cycling study of protein A chromatography. Two approaches have been considered to detect anomalies in case of column integrity breach. The first approach utilized the traditional Principal Component Analysis (PCA) method for dimensionality reduction followed by anomaly detection using Isolation Forest (IF) algorithm. The second approach involved the application of deep learning neural network based Long Short Term Memory autoencoder (LSTM AE). Both the algorithms could successfully predict the column integrity failure 4 cycles ahead of the actual cycle. In the case of prediction of percentage yield decay, a partial least squares-artificial neural network (PLS-ANN) augmented model was utilized and compared with the traditional PLS regression model. The developed PLS-ANN model with higher R2 and lower RMSE values of 0.96 and 0.014 respectively could outperform the classical PLS model with lower R2 and RMSE values of 0.88 and 0.028, resulting in more accurate yield prediction. The developed ML algorithms for both case studies could not only successfully forecast anomalies by detecting subtle changes in column packing quality and thereby facilitate real time control decisions for preventive measures, a prerequisite for continuous manufacturing, but also demonstrated the ability to predict complex yield decay behaviour for protein A chromatography. As biopharmaceutical manufacturing adopts continuous processing, copious amount of data will be generated from the process and analytical equipment on the manufacturing floor, and the proposed advanced ML algorithms have significant potential in dealing with nonlinearities of the different unit operations simultaneously and facilitate real-time control decision making.

An Early Warning System for Earthquake Prediction from Seismic Data Using Batch Normalized Graph Convolutional Neural Network with Attention Mechanism (BNGCNNATT).

Earthquakes threaten people, homes, and infrastructure. Early warning systems provide prior warning of oncoming significant shaking to decrease seismic risk by providing location, magnitude, and depth information of the event. Their usefulness depends on how soon a strong shake begins after the warning. In this article, the authors implement a deep learning model for predicting earthquakes. This model is based on a graph convolutional neural network with batch normalization and attention mechanism techniques that can successfully predict the depth and magnitude of an earthquake event at any number of seismic stations in any number of locations. After preprocessing the waveform data, CNN extracts the feature map. Attention mechanism is used to focus on important features. The batch normalization technique takes place in batches for stable and faster training of the model by adding an extra layer. GNN with extracted features and event location information predicts the event information accurately. We test the proposed model on two datasets from Japan and Alaska, which have different seismic dynamics. The proposed model achieves 2.8 and 4.0 RMSE values in Alaska and Japan for magnitude prediction, and 2.87 and 2.66 RMSE values for depth prediction. Low RMSE values show that the proposed model significantly outperforms the three baseline models on both datasets to provide an accurate estimation of the depth and magnitude of small, medium, and large-magnitude events.

Prediction of acute toxicity of pesticides for Americamysis bahia using linear and nonlinear QSTR modelling approaches

Globally, pesticides are toxic substances with wide applications. However, the widespread use of pesticides has received increasing attention from regulatory agencies due to their various acute and chronic effects on multiple organisms. In this study, Quantitative Structure-Toxicity Relationship (QSTR) models were established using Multiple Linear Regression (MLR) and five Machine Learning (ML) algorithms to predict pesticide toxicity in Americamysis bahia. The most influential descriptors included in the MLR model are RBF, JGI2, nCbH, nRCOOR, nRSR, nPO4 and ‘Cl-090’, with positive contributions to the dependent variable (negative decimal logarithm of median lethal concentration at 96-h). The Random Forest (RF) regression model was superior amongst the five ML models. We observed higher values of R2 (0.812) and lower values of RMSE (0.595) and MAE (0.462) in the cross-validation training set and external validation set. Similarly, this study had a high level of fitness and was internally robust and externally predictive compared to models presented in similar studies. The results suggest that the developed QSTR models are suitable for reliably predicting the aquatic toxicity of structurally diverse pesticides and can be used for screening, prioritising new pesticides, filling data gaps and overcoming the limitations of in vivo and in vitro tests.

Estimating aboveground biomass changes in a human-modified tropical montane forest of Borneo using multi-temporal airborne LiDAR data

Estimating aboveground biomass changes in tropical mountains is difficult due to the small-scale anthropogenic land use activities such as selective logging. This study examined how multi-temporal airborne LiDAR data could estimate AGB changes in Borneo's tropical montane forest. Using airborne LiDAR data acquired in 2012 and 2017, we compared direct and indirect approaches to estimating the AGB changes. The direct method predicts the AGB change directly based on differences in LiDAR variables between the two time points whereas, the indirect method first constructs a model for predicting the AGB for each time point and then estimates the changes. The direct approach produced a model with an adjusted R2 of 0.321 and a relatively high RMSE (6.37 Mg/ha/year; relative RMSE: 134.36%). On the other hand, annual AGB changes derived from the indirect approach had a low RMSE value (1.413 Mg/ha/year; relative RMSE: 29.80%) and were strongly correlated with the field AGB changes (R2 = 0.988). We estimated the AGB changes using the indirect approach to be −7.49 Mg/ha/year for AGB loss and 8.91 Mg/ha/year for AGB gain. We identified land use conversion as the primary driver of AGB changes in the montane forest since the rate of AGB decrease in state-land was higher than in the managed forest. The LiDAR-based approach provides high-resolution estimates of AGB changes by enlarging field plots to more extensive area coverage, facilitating the adoption of incentive-based carbon conservation mechanisms.

Estimation and uncertainty analysis of groundwater quality parameters in a coastal aquifer under seawater intrusion: a comparative study of deep learning and classic machine learning methods.

Excessive withdrawal of groundwater for agricultural irrigation can cause seawater intrusion into coastal aquifers. Such a case will in turn results in deterioration of irrigation water quality. Determination of irrigation water quality with traditional methods is a time-consuming and costly process. However, machine learning algorithms can be useful tools for modeling and estimating groundwater quality used for irrigation water purposes. In this study, TDS, PS, SAR, and Cl parameters of groundwater were estimated with models based on EC and pH variables. For this purpose, prediction performances of two different deep learning methods (convolutional neural network (CNN) and deep neural network (DNN)) and two different classical machine learning (Random Forest (RF) and extreme gradient boosting (XGBoost)) methods were compared. In addition, predictive uncertainty of the models was determined by quantile regression (QR) analysis. Performance criteria and results of uncertainty analysis revealed that CNN (in testing phase, NSE = 0.95 for TDS, NSE = 0.96 for PS, NSE = 0.67 for SAR and NSE = 0.93 for CI) and DNN (in testing phase, NSE = 0.91 for TDS, NSE = 0.91 for PS, NSE = 0.57 for SAR and NSE = 0.94 for Cl) models had quite a close performance in estimation of TDS, PS, SAR, and Cl parameters and higher than the other two classical machine learning methods. As a result, the CNN model can be considered the best performing model in estimating all quality parameters due to the highest NSE and lowest RMSE values. In addition, the Taylor diagram showed that the values estimated using the CNN model had the highest correlation with the measured data. It was determined that the model with the lowest uncertainty based on the PICP statistics was DNN, followed by the CNN model. However, the CNN model has predicted outliers more accurately. Present findings proved that deep learning models could offer efficient tools for predicting irrigation water quality parameters.

Estimating the Optimal Threshold for Accuracy Assessment of the Global Ecosystem Dynamics Investigation (GEDI) Data in a Gentle Relief Urban Area

LiDAR is an excellent source of elevation data used in many surveys. The spaceborne handle system, Global Ecosystem Dynamics Investigation (GEDI), provides ground elevation information with high accuracy except for areas with steep slopes. GEDI data have a lot of noise from atmospheric conditions, and therefore filtering procedures are mandatory to select the best dataset. The dataset presents uncertainties of different magnitudes, with values reaching more than 100 m of difference between the reference data and the GEDI data. The challenge is to find a criterion to determine a threshold to filter accurate GEDI samples. This research aims to identify the threshold based on the difference values between the reference data and the GEDI data to select the maximum number of samples with low RMSE values. Therefore, we used the Kolmogorov–Smirnov (KS) non-parametric test to define the best threshold based on a normal distribution. Our results demonstrated a lower RMSE value with a high number of samples when compared with the quality flag parameter threshold, even using sensitivity parameter thresholds. This method is useful for achieving the best possible accuracy from GEDI data worldwide.

Data Mining Algorithms for Operating Pressure Forecasting of Crude Oil Distribution Pipelines to Identify Potential Blockages

The implementation of data mining has become very popular in many fields recently, including in the petroleum industry. It is widely used to help in decision-making processes in order to minimize oil losses during operations. One of the major causes of loss is oil flow blockages during transport to the gathering facility, known as the congeal phenomenon. To overcome this situation, real-time surveillance is used to monitor the oil flow condition inside pipes. However, this system is not able to forecast the pipeline pressure on the next several days. The objective of this study is to forecast the pressure several days in advance using real-time pressure data, as well as external factor data recorded by nearby weather stations, such as ambient temperature and precipitation. Three machine learning algorithms—multi-layer perceptron (MLP), long short-term memory (LSTM), and nonlinear autoregressive exogenous model (NARX)—are evaluated and compared with each other using standard regression evaluation metrics, including a steady-state model. As a result, with proper hyperparameters, in the proposed method of NARX with MLP as a regressor, the NARX algorithm showed the best performance among the evaluated algorithms, indicated by the highest values of R2 and lowest values of RMSE. This algorithm is capable of forecasting the pressure with high correlation to actual field data. By forecasting the pressure several days ahead, system owners may take pre-emptive actions to prevent congealing.

An Explainable Evolving Fuzzy Neural Network to Predict the k Barriers for Intrusion Detection Using a Wireless Sensor Network.

Evolving fuzzy neural networks have the adaptive capacity to solve complex problems by interpreting them. This is due to the fact that this type of approach provides valuable insights that facilitate understanding the behavior of the problem being analyzed, because they can extract knowledge from a set of investigated data. Thus, this work proposes applying an evolving fuzzy neural network capable of solving data stream regression problems with considerable interpretability. The dataset is based on a necessary prediction of k barriers with wireless sensors to identify unauthorized persons entering a protected territory. Our method was empirically compared with state-of-the-art evolving methods, showing significantly lower RMSE values for separate test data sets and also lower accumulated mean absolute errors (MAEs) when evaluating the methods in a stream-based interleaved-predict-and-then-update procedure. In addition, the model could offer relevant information in terms of interpretable fuzzy rules, allowing an explainable evaluation of the regression problems contained in the data streams.

Determination of rice (Oryza sativa L.) site suitability using multi-criteria decision-making based on the best-worst method

The goal of this study was to identify the best convenient fields for rice (Oryza sativa L.) production utilizing BWM-GIS integration based on some physico-chemical and productivity properties of the soils formed on Çarşamba Plain. Nine soil quality parameters rest on the crucial predictor variables defining rice yield were subsumed into RSI model. Exponential semivariogram model of OK was determined as the lowest RMSE value (0.7290) to generate distribution map. According to result map, it was found that the greatest RSI value was in Vertisol soils and the lowest RSI value was in Entisol soils. In addition, although high clay content, the soils classified as Typic Calciustert were put among low RSI classes in quality assessment because of their high slope. The bio-physical plans and land suitability analyses for rice cultivation can assist the conserving of the environment and to aid for decision makers considering future land use policy.