Application of geographically weighted regression model to analysis of spatiotemporal varying relationships between groundwater quantity and land use changes (case study: Khanmirza Plain,Iran)

Understanding the spatiotemporal relationships between land use/cover changes (LUCC) and groundwater resources is necessary for effective and efficient land use management. In this paper, geographically weighted regression (GWR) and ordinary least squares (OLS) models have been expanded to analyze varying spatial relationships between groundwater quantity changes and LUCC for three periods: 1987–2000, 2000–2010, and 1987–2010 in the Khanmirza Plain of southwestern Iran. For this purpose, TM images were used to generate LUCC (rainfed, irrigated, meadow, and bare lands). Groundwater quantity variables, including groundwater level changes (GLC) and groundwater withdrawal differences (GWD), were gathered from piezometric and agricultural wells data. The analysis of spatial autocorrelation (Moran’s I and local indicators of spatial association ) demonstrated that GWR has a better ability to model spatially varying data with very minimal clustering of residuals. The results R ² and corrected Akaike’s Information Criterion parameters revealed that the GWR has the lowest similarity in space and time in neighboring situations and it has the high ability to explain more variance in the LUCC as a function of the groundwater quantity changes. All results of the distribution of local R ² values from GWR confirm our assertion that there is a spatiotemporal relationship between types of land use and each of groundwater quantity variables within the region. According to the t test results from GWR, there are significant differences between the GLC and GWD and the land use types in different places of region in each of the three time series. The GWR results can help decision-makers to make appropriate decisions for future planning.     

基于LSTM-GCN的PM2.5浓度预测模型

应用机器学习算法开展空气质量预测已成为当前研究热点之一,空气质量监测数据具有显著的时空特征,即具有时间维度时序特征和空间维度传输演化特征。面向空气质量监测数据,联合LSTM提取的时间特征和GCN提取的空间特征,提出预测PM_2.5浓度的LSTM-GCN组合模型。以北京市35个空气质量监测站2018—2020年监测数据进行仿真实验,并将LSTM-GCN模型与LSTM模型、GCN模型以及时空地理加权回归模型(GTWR)进行对比,结果显示:LSTM-GCN模型相较于LSTM模型均方根误差(RMSE)、平均绝对误差(MAE)分别降低了11.68%、7.34%;相较于GCN模型RMSE、MAE分别降低了40.22%、36.37%;相较于GTWR模型RMSE、MAE分别降低了17.52%、23.69%,表明所提出LSTM-GCN模型在准确率上有所提升。用LSTM-GCN模型预测2021年1—7月PM_2.5浓度,结果显示预测效果较好。     

Assessment of Spatiotemporal Varying Relationships Between Rainfall,Land Cover and Surface Water Area Using Geographically Weighted Regression

Traditional regression techniques such as ordinary least squares (OLS) are often unable to accurately model spatially varying data and may ignore or hide local variations in model coefficients. A relatively new technique, geographically weighted regression (GWR) has been shown to greatly improve model performance compared to OLS in terms of higher R ² and lower corrected Akaike information criterion (AIC_C). GWR models have the potential to improve reliabilities of the identified relationships by reducing spatial autocorrelations and by accounting for local variations and spatial non-stationarity between dependent and independent variables. In this study, GWR was used to examine the relationship between land cover, rainfall and surface water habitat in 149 sub-catchments in a predominately agricultural region covering 2.6 million ha in southeast Australia. The application of the GWR models revealed that the relationships between land cover, rainfall and surface water habitat display significant spatial non-stationarity. GWR showed improvements over analogous OLS models in terms of higher R ² and lower AIC_C. The increased explanatory power of GWR was confirmed by the results of an approximate likelihood ratio test, which showed statistically significant improvements over analogous OLS models. The models suggest that the amount of surface water area in the landscape is related to anthropogenic drainage practices enhancing runoff to facilitate intensive agriculture and increased plantation forestry. However, with some key variables not present in our analysis, the strength of this relationship could not be qualified. GWR techniques have the potential to serve as a useful tool for environmental research and management across a broad range of scales for the investigation of spatially varying relationships.     

Estimation of spatial distrubition of groundwater level and risky areas of seawater intrusion on the coastal region in Çarşamba Plain,Turkey, using different interpolation methods

Groundwater level plays a significant role in coastal plains. Heavy pumping and excessive use of near-coast groundwater can increase the intrusion of seawater into the aquifers. In the present study, groundwater levels were measured at 59 groundwater wells at different times during pre- and post-irrigation seasons (April and September of the year 2012) in Çar?amba Plain, Turkey. To select the best method, two deterministic interpolation methods (inverse distance weighing (IDW) with the weights of 1, 2, and 3 and radial basis function (RBF) with spline with tension (SPT) and completely regularized spline (CRS)) and two stochastic methods (ordinary kriging (OK) with spherical, exponential, and Gaussian variograms) and cokriging (COK)) were compared and then the best interpolation method was used to evaluate the spatial distribution of groundwater levels in different seasons and seasonal changes. A total of nine different techniques were tested. Also, risky areas of seawater intrusion in coastal area were determined using the best methods for two periods. The performance of these interpolation methods is evaluated by using a validation test method. Statistical indices of correlation (R ²), mean absolute error (MAE), and root-mean-square error (RMSE) were used to select and validate the best methods. Comparisons between predicted and observed values indicated RBF as the optimal method for groundwater level estimation in April and September. When the best method RBF and the worst method IDW were compared, significant differences were observed in the spatial distribution of groundwater. Results of the study also revealed that excessive groundwater withdrawals during the post-irrigation season dropped the groundwater levels up to 2.0 m in some sections. With regard to seawater intrusion, 9,103 ha of land area was determined to be highly risky and risky.     

Advantages of Geographically Weighted Regression for Modeling Benthic Substrate in Two Greater Yellowstone Ecosystem Streams

Stream habitat assessments are commonplace in fish management, and often involve nonspatial analysis methods for quantifying or predicting habitat, such as ordinary least squares regression (OLS). Spatial relationships, however, often exist among stream habitat variables. For example, water depth, water velocity, and benthic substrate sizes within streams are often spatially correlated and may exhibit spatial nonstationarity or inconsistency in geographic space. Thus, analysis methods should address spatial relationships within habitat datasets. In this study, OLS and a recently developed method, geographically weighted regression (GWR), were used to model benthic substrate from water depth and water velocity data at two stream sites within the Greater Yellowstone Ecosystem. For data collection, each site was represented by a grid of 0.1 m² cells, where actual values of water depth, water velocity, and benthic substrate class were measured for each cell. Accuracies of regressed substrate class data by OLS and GWR methods were calculated by comparing maps, parameter estimates, and determination coefficient r ². For analysis of data from both sites, Akaike’s Information Criterion corrected for sample size indicated the best approximating model for the data resulted from GWR and not from OLS. Adjusted r ² values also supported GWR as a better approach than OLS for prediction of substrate. This study supports GWR (a spatial analysis approach) over nonspatial OLS methods for prediction of habitat for stream habitat assessments.     

The effectiveness of digital soil mapping to predict soil properties over low-relief areas

This study investigates the ability of different digital soil mapping (DSM) approaches to predict some of physical and chemical topsoil properties in the Shahrekord plain of Chaharmahal-Va-Bakhtiari province, Iran. According to a semi-detailed soil survey, 120 soil samples were collected from 0 to 30 cm depth with approximate distance of 750 m. Particle size distribution, coarse fragments (CFs), electrical conductivity (EC), pH, organic carbon (OC), and calcium carbonate equivalent (CCE) were determined. Four machine learning techniques, namely, artificial neural networks (ANNs), boosted regression tree (BRT), generalized linear model (GLM), and multiple linear regression (MLR), were used to identify the relationship between soil properties and auxiliary information (terrain attributes, remote sensing indices, geology map, existing soil map, and geomorphology map). Root-mean-square error (RMSE) and mean error (ME) were considered to determine the performance of the models. Among the studied models, GLM showed the highest performance to predict pH, EC, clay, silt, sand, and CCE, whereas the best model is not necessarily able to make accurate estimation. According to RMSE%, DSM has a good efficiency to predict soil properties with low and moderate variabilities. Terrain attributes were the main predictors among different studied auxiliary information. The accuracy of the estimations with more observations is recommended to give a better understanding about the performance of DSM approach over low-relief areas.     

Spatial interpolation of ambient ozone concentrations from sparse monitoring points in Belgium

Due to scientific interest on the one hand and political and regulatory obligations on the other hand the monitoring of ozone in the troposphere is an important issue. To this end, in Belgium as in many other countries, a fixed network of monitoring stations is operated. In order to estimate the ozone concentrations over the whole territory, a model is needed to spatially complement the sparse measurements. This paper describes the development of an interpolation scheme which is aimed at fast operational use. The model uses the population density as auxiliary data to remove a spatial trend due to titration by nitric oxide. The residuals are interpolated by kriging. As a benchmark the inverse distance weighting interpolation method is used with and without the detrending. The proposed model systematically improves the interpolation and makes a significant difference when estimating human exposure to ozone. It is generic in design, easy to implement and flexible to changes in the monitoring network.     

Spatial Prediction of Stream Temperatures Using Top-Kriging with an External Drift

Top-kriging is a method for estimating stream flow and stream flow-related variables on a river network. Top-kriging treats these variables as emerging from a two-dimensional spatially continuous process in the landscape. The top-kriging weights are estimated by a family of variogram models (regularisations) for different catchment areas (kriging support), which accounts for the different scales and the nested nature of the catchments. This assures that kriging weights are distributed to both hydrologically connected and unconnected sites of the stream network according to the data situation: top-kriging gives most weight to close-by sites at the same river system, but when the next hydrologically connected site is far away, more weight is given to a close-by site at an adjacent river system. The distribution of weights is in contrast to ordinary kriging and stream distance-based kriging which does not account for both spatial proximity and network connectivity. We extend the top-kriging method by incorporating an external drift function to account for the deterministic patterns of the spatial variable. We test the method for a comprehensive Austrian stream temperature dataset. The drift is modelled by exponential regression with catchment altitude. Top-kriging is then applied to the regression residuals. The variogram used in top-kriging is fitted by a semiautomatic optimisation procedure. A leave-one-out cross-validation analysis shows that the model performs well for the study domain. The residual mean squared error (cross-validation) decreases by 20 % when using top-kriging in addition to the regression model. For regions where the observed stream temperatures deviate from the expected value of the drift model, top-kriging corrects these regional biases. By exploiting the topological information of the stream network, top-kriging is able to improve the local adjustment of the drift model for the main streams and the tributaries.     

Mapping the organic carbon stocks of surface soils using local spatial interpolator

The largest uncertainties are associated with estimating the soil organic carbon (SOC) stock because of natural soil variability and data scarcity. Thus, a local spatial geostatistical hybrid approach, the geographically weighted regression kriging (GWRK), was used in the present study to overcome some of these uncertainties. This study was designed to estimate the SOC stock (kg C m(-2)) for the surface 0 to 15 cm depth using the state of Pennsylvania as the study region. A total of 920 soil profiles were extracted from the National Soil Survey Center database and were divided into calibration (80%) and validation (20%) periods. Some soil parameters that include clay content, bulk density (ρ(b)), total nitrogen (TN) content, pH, Ca(2+), Na(+), extractable acidity (EXACID), and cation exchange capacity (CEC) were used as covariates for estimating the SOC stock. These covariates exhibited spatial autocorrelation (Moran's Index, I = 0.62 to 0.89). Further, residuals of geographically weighted regression were spatially autocorrelated, and hence support the use of the GWRK approach. Validation results concluded that the performance of the GWRK approach was the best with the lowest values of root mean square error, mean estimation error and mean absolute estimation error. The estimated SOC stock for the surface 0 to 15 cm depth ranged from 1.41 to 3.94 kg m(-2). Results from this study show that the GWRK captures spatial dependent relationships, and addresses spatial non-stationarity issues, hence this approach improves the estimations of SOC stock.     

合肥市生活垃圾产量多模型预测与分析

针对合肥市生活垃圾产量现状,通过建立时间序列(ARIMA)、多元线性回归(MLR)、灰色系统GM(1,1)和反向传播神经网络(BPNN)模型对历史数据进行验证比较分析。结果表明,ARIMA(0,1,2)模型的MAPE、MAE、RMSE、NRMSE分别为1.879%、2.240、2.781、0.021,其精度最高、效果最好,为合肥市生活垃圾产量的最佳预测模型。用该模型预测合肥市2021—2025年的城市生活垃圾产量,结果显示生活垃圾产生量为218.89万t～290.71万t。     

Generalized regression neural network (GRNN)-based approach for colored dissolved organic matter (CDOM) retrieval: case study of Connecticut River at Middle Haddam Station,USA

The prediction of colored dissolved organic matter (CDOM) using artificial neural network approaches has received little attention in the past few decades. In this study, colored dissolved organic matter (CDOM) was modeled using generalized regression neural network (GRNN) and multiple linear regression (MLR) models as a function of Water temperature (TE), pH, specific conductance (SC), and turbidity (TU). Evaluation of the prediction accuracy of the models is based on the root mean square error (RMSE), mean absolute error (MAE), coefficient of correlation (CC), and Willmott’s index of agreement (d). The results indicated that GRNN can be applied successfully for prediction of colored dissolved organic matter (CDOM).     

Groundwater quality assessment and its correlation with gastroenteritis using GIS: a case study of Rawal Town,Rawalpindi, Pakistan

Majority of the people of Pakistan get drinking water from groundwater source. Nearly 40 % of the total ailments reported in Pakistan are the result of dirty drinking water. Every summer, thousands of patients suffer from acute gastroenteritis in the Rawal Town. Therefore, a study was designed to generate a water quality index map of the Rawal Town and identify the relationship between bacteriological water quality and socio-economic indicators with gastroenteritis in the study area. Water quality and gastroenteritis patient data were collected by surveying the 262 tubewells and the major hospitals in the Rawal Town. The collected spatial data was analyzed by using ArcGIS spatial analyst (Moran’s I spatial autocorrelation) and geostatistical analysis tools (inverse distance weighted, radial basis function, kriging, and cokriging). The water quality index (WQI) for the study area was computed using pH, turbidity, total dissolved solids, calcium, hardness, alkalinity, and chloride values of the 262 tubewells. The results of Moran’s I spatial autocorrelation showed that the groundwater physicochemical parameters were clustered. Among IDW, radial basis function, and kriging and cokriging interpolation techniques, cokriging showed the lowest root mean square error. Cokriging was used to make the spatial distribution maps of water quality parameters. The WQI results showed that more than half of the tubewells in the Rawal Town were providing “poor” to “unfit” drinking water. The Pearson’s coefficient of correlation for gastroenteritis with fecal coliform was found significant (P?P?P?相似文献   

Evaluating Kriging as a Tool to Improve Moderate Resolution Maps of Forest Biomass

The USDA Forest Service, Forest Inventory and Analysis program (FIA) recently produced a nationwide map of forest biomass by modeling biomass collected on forest inventory plots as nonparametric functions of moderate resolution satellite data and other environmental variables using Cubist software. Efforts are underway to develop methods to enhance this initial map. We explored the possibility of modeling spatial structure to make such improvements. Spatial structure in the field biomass data as well as in residuals from the map was investigated across 18 ecological zones in the Interior Western U.S. Exploratory tools included directional graphs of summary statistics, three dimensional maps, Moran’s I correlograms, and variograms. Where spatial pattern was present, field and residual biomass were kriged, and predictions made for an independent test set were evaluated for improvement over predictions in the initial biomass map. While kriging has some potential benefit when analyzing the field data and exploring spatial structure, kriging residuals resulted in little or no improvement in the initial biomass map developed using Cubist software. Stationarity assumptions, variogram behavior, and appropriate model fitting strategies are discussed.     

Spatial modeling of forest stand susceptibility to logging operations

The susceptibility of residual, non-harvested, live trees to damage caused by the harvesting of other nearby trees has received moderate attention over the last four decades through observational studies prompted by concerns over ecological and economic consequences of logging operations. We developed models to predict the potential level of damage to residual trees that could be caused by selective timber harvesting. Three machine-learning methods, i.e., classification and regression tree (CART), random forest (RF), and boosted regression tree (BRT), were assessed for this purpose. Through an observational study of a harvested area in the Hyrcanian forests of Iran, we recorded damage to trees >7.5 cm diameter at breast height along transects and grouped them into three types: (1) scars >100 cm², (2) >50% crown removal, and (3) trees leaning >10°. These field observations were associated with the spatially explicit characteristics of the forest stand, i.e., slope angle, slope aspect, altitude, slope length, topographic position index, stand type, stand density, and distance from the nearest roads and skid trails, that were considered as the explanatory variables to the modeling processes. To determine whether the CART, RF, and BRT models performed well in estimating the probability of damage occurrence, they were validated using the Akaike information criterion (AIC) and area under the receiver operating characteristics (AUC) curve. The results revealed that the BRT model with AIC = −276 and AUC = 0.89 generated the most accurate spatially explicit distribution map of stand susceptibility to damage from logging operations, followed by RF (AIC = −263 and AUC = 0.87) and CART (AIC = −23 and AUC = 0.62). We found that the spatial extent of residual stand damage was highly influenced by slope terrain and stand density. Our study has practical implications for reorganizing and planning reduced-impact logging operations and provides forest engineers with insights into the utility of machine learning methods in domains of forestry and forest engineering.     

Mapping aboveground woody biomass using forest inventory,remote sensing and geostatistical techniques

Mapping forest biomass is fundamental for estimating CO₂ emissions, and planning and monitoring of forests and ecosystem productivity. The present study attempted to map aboveground woody biomass (AGWB) integrating forest inventory, remote sensing and geostatistical techniques, viz., direct radiometric relationships (DRR), k-nearest neighbours (k-NN) and cokriging (CoK) and to evaluate their accuracy. A part of the Timli Forest Range of Kalsi Soil and Water Conservation Division, Uttarakhand, India was selected for the present study. Stratified random sampling was used to collect biophysical data from 36 sample plots of 0.1 ha (31.62 m?×?31.62 m) size. Species-specific volumetric equations were used for calculating volume and multiplied by specific gravity to get biomass. Three forest-type density classes, viz. 10–40, 40–70 and >70 % of Shorea robusta forest and four non-forest classes were delineated using on-screen visual interpretation of IRS P6 LISS-III data of December 2012. The volume in different strata of forest-type density ranged from 189.84 to 484.36 m³ ha^?1. The total growing stock of the forest was found to be 2,024,652.88 m³. The AGWB ranged from 143 to 421 Mgha^?1. Spectral bands and vegetation indices were used as independent variables and biomass as dependent variable for DRR, k-NN and CoK. After validation and comparison, k-NN method of Mahalanobis distance (root mean square error (RMSE)?=?42.25 Mgha^?1) was found to be the best method followed by fuzzy distance and Euclidean distance with RMSE of 44.23 and 45.13 Mgha^?1 respectively. DRR was found to be the least accurate method with RMSE of 67.17 Mgha^?1. The study highlighted the potential of integrating of forest inventory, remote sensing and geostatistical techniques for forest biomass mapping.     

Community analysis in stream biomonitoring: what we measure and what we don't

Diatom assemblages from 83 epilithic samples taken from the Mesta River, Bulgaria, were regressed against three sets of predictor variables, i.e. environmental, spatial, and temporal. Redundancy analysis (RDA) of species and environmental data explained 36% of the diatom variance and extracted several important gradients of species distribution, associated with a downstream increase in nutrient levels, pH, temperature, and organic pollution. The inclusion of spatial and temporal variables in the RDA model captured additional 24% of the diatom variance and revealed three more gradients, a spatial gradient represented by higher order polynomial terms of latitude and longitude, and two temporal gradients of annual and seasonal variation. Partial RDAs demonstrated that the unique contribution of each predictor set to the explained diatom variance was the highest in the spatial dataset (16%), followed by the environmental (9%), and the temporal (7%) datasets. The remaining 28% of the variance was explained by the covariance of the predictor sets. This suggests that in biomonitoring of single stream basins, the cheap and simple account of space and time would explain most of the variance in assemblage composition obviating the necessity of expensive and time-consuming environmental assessments. The nature of the underlying environmental mechanisms can be easily inferred from the diatom composition itself.     

Modeling seasonal variations of long-term soil CO<Subscript>2</Subscript> emissions in an orchard plantation in a semiarid area,SE Turkey

Emissions of soil CO₂ under different management systems have a significant effect on the carbon balance in the atmosphere. Soil CO₂ emissions were measured from an apricot orchard at two different locations: under the crown of trees (CO₂-UC) and between tree rows (CO₂-BR). For comparison, one other measurement was performed on bare soil (CO₂-BS) located next to the orchard field. Analytical data were obtained weekly during 8 years from April 2008 to December 2016. Various environmental parameters such as air temperature, soil temperature at different depths, soil moisture, rainfall, and relative humidity were used for modeling and estimating the long-term seasonal variations in soil CO₂ emissions using two different methods: generalized linear model (GLM) and artificial neural network (ANN). Before modeling, data were randomly split into two parts, one for calibration and the second for validation, with a varying number of samples in each part. Performances of the models were compared and evaluated using means absolute of estimations (MAE), square root of mean of prediction (RMSEP), and coefficient of determination (R²) values. CO₂-UC, CO₂-BR, and CO₂-BS values ranged from 11 to 3985, from 9 to 2365, and from 8 to 1722 kg ha^?1 week^?1, respectively. Soil CO₂ emissions were significantly correlated (p?<?0.05) with some environmental variables. The results showed that GLM and ANN models provided similar accuracies in modeling and estimating soil CO₂ emissions, as the number of samples in the validation data set increased. The ANN was more advantageous than GLM models by providing a better fit between actual observations and predictions and lower RMSEP and MAE values. The results suggested that the success of environmental variables for estimations of CO₂ emissions using the two methods was moderate.     

Estimation of soil specific surface area using some mechanical properties of soil by artificial neural networks

Soil specific surface area (SSA) is an important property of soil. Depending on the measurement techniques, determination of the SSA is costly and time consuming. Hence, a limited number of studies have been conducted to predict the SSA from the soil variables. In this study, the soil samples were taken from the literature. Fractal parameters (FP) were calculated by the model of Bird et al. (European Journal of Soil Science 51, 55–63, 2000) used as the input variables to predict the SSA. Some studies have been carried out on the prediction capability of the different parameters using the artificial neural networks (ANNs). The ANNs were further used and 20 models were developed to investigate the value of input variables to predict the SSA. The results showed that the PTF13 (RMSE?=?0.13) and PTF18 (RMSE?=?0.13) with the input variables of particle-size distribution and Atterberg limits revealed better performance than the other PTFs (in the training step). It is because of the fact that free swelling index (FSI) and Atterberg limits were closely correlated to the soil clay mineralogy as one of the important factors controlling the SSA. In general, this results demonstrated that the PTF9 with the variables of sand, clay, plastic limit (PL), liquid limit (LL), and FSI showed the best (RMSE?=?0.37) results in the estimation of the SSA. In conclusion, there was not a strong correlation between the soil mechanical properties and SSA but also ANNs were a suitable method to predict the SSA from the soil variables.     

Monitoring diel dissolved oxygen dynamics through integrating wavelet denoising and temporal neural networks

Diel dissolved oxygen (DO) time series measured continuously using proximal sensors in situ for a temperate lake were denoised using discrete wavelet transform (DWT) with the orthogonal wavelet families of coiflet, daubechies, and symmlet with order of 10. Diel DO time series denoised were modeled using nine temporal artificial neural networks (ANNs) as a function of water level, water temperature, electrical conductivity, pH, day of year, and hour. Our results showed that time-lag recurrent network (TLRN) using denoised data emulated diel DO dynamics better than the best-performing TLRN using the original data, time-delay neural network (TDNN), and recurrent network (RNN). Daubechies basis dealt with diel DO data slightly better than the other bases given its coefficient of determination (r ²?=?87.1 %), while symmlet performed slightly better than the other bases in terms of root mean square error (RMSE?=?1.2 ppm) and mean absolute error (MAE?=?0.9 ppm).     

Development of GP and GEP models to estimate an environmental issue induced by blasting operation

Air overpressure (AOp) is one of the most adverse effects induced by blasting in the surface mines and civil projects. So, proper evaluation and estimation of the AOp is important for minimizing the environmental problems resulting from blasting. The main aim of this study is to estimate AOp produced by blasting operation in Miduk copper mine, Iran, developing two artificial intelligence models, i.e., genetic programming (GP) and gene expression programming (GEP). Then, the accuracy of the GP and GEP models has been compared to multiple linear regression (MLR) and three empirical models. For this purpose, 92 blasting events were investigated, and subsequently, the AOp values were carefully measured. Moreover, in each operation, the values of maximum charge per delay and distance from blast points, as two effective parameters on the AOp, were measured. After predicting by the predictive models, their performance prediction was checked in terms of variance account for (VAF), coefficient of determination (CoD), and root mean square error (RMSE). Finally, it was found that the GEP with VAF of 94.12%, CoD of 0.941, and RMSE of 0.06 is a more precise model than other predictive models for the AOp prediction in the Miduk copper mine, and it can be introduced as a new powerful tool for estimating the AOp resulting from blasting.