Using neural networks and remote sensing for spatio-temporal prediction of air pollution during the COVID-19 pandemic.

The study aims to monitor air pollution in Iranian metropolises using remote sensing, specifically focusing on pollutants such as O3, CH4, NO2, CO2, SO2, CO, and suspended particles (aerosols) in 2001 and 2019. Sentinel 5 satellite images are utilized to prepare maps of each pollutant. The relationship between these pollutants and land surface temperature (LST) is determined using linear regression analysis. Additionally, the study estimates air pollution levels in 2040 using Markov and Cellular Automata (CA)-Markov chains. Furthermore, three neural network models, namely multilayer perceptron (MLP), radial basis function (RBF), and long short-term memory (LSTM), are employed for predicting contamination levels. The results of the research indicate an increase in pollution levels from 2010 to 2019. It is observed that temperature has a strong correlation with contamination levels (R2 = 0.87). The neural network models, particularly RBF and LSTM, demonstrate higher accuracy in predicting pollution with an R2 value of 0.90. The findings highlight the significance of managing industrial towns to minimize pollution, as these areas exhibit both high pollution levels and temperatures. So, the study emphasizes the importance of monitoring air pollution and its correlation with temperature. Remote sensing techniques and advanced prediction models can provide valuable insights for effective pollution management and decision-making processes.

Thermal power plants pollution assessment based on deep neural networks, remote sensing, and GIS: A real case study in Iran.

To investigate the impact of the Bandar Abbas thermal power plant on the waters of the Persian Gulf coast, a combination of satellite images and ground data was utilized to determine the Sea Surface Temperature (SST) as a thermal index, Total Organic Carbon (TOC) and Chemical Oxygen Demand (COD) as biological indices. Additionally, measurements of SO2, O3, NO2, CO2, CO, and CH4 values in the atmosphere were taken to determine the plant's impact on air pollution. Temperature values of the water for different months were predicted using Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and Cascade neural networks. The results indicate that the waters near thermal power plants exhibit the highest temperatures in July and September, with temperatures reaching approximately 50 °C. Furthermore, the SST values were found to be strongly correlated with ecological indices. The Multiple Linear Regression (MLR) analysis revealed a strong correlation between the temperature and TOC, COD, and O2 in water (RTOC2=0.98), [Formula: see text] , RCOD2=0.87 and O3, NO3, CO2, and CO in the air ( [Formula: see text] ). Finally, the results demonstrate that the LSTM method exhibited high accuracy in predicting the water temperature (R2 = 0.98).

Investigating the pollution of irrigated plants (Rosmarinus officinalis) with polluted water in different growth stages using spectrometer and K-means method.

Rosmarinus officinalis is a widely cultivated plant with various medicinal and culinary uses. However, irrigation with contaminated water can lead to the accumulation of heavy elements in the tissues of this plant. Therefore, the purpose of this study was to investigate the contamination of Rosmarinus officinalis with heavy elements during irrigation with polluted water (wastewater). To achieve this, 39 seedlings were uniformly planted in pots and irrigated with water contaminated with zinc, lead, nickel, and cadmium. The level of contamination in the plant was measured at three vegetative stages using target hazard quotient (THQ), hazard index (HI), and bioconcentration factor (BCF) indicators. In addition, a spectrometer in the range of 400-1030 nm was used to measure the amount of reflection of plants to electromagnetic waves. The K-means method was then applied to investigate the relationship between the morphological characteristics of the plants and heavy metal pollution. The results showed that the highest THQ values were observed in the third vegetative stage (THQPb = 113, THQNi = 0.08, THQZn = 0.25, THQCd = 0.1). Furthermore, the BCFCd and BCFPb indices indicated that the highest contamination levels occurred in the third vegetative stage. The regression analysis identified the spectral bands of 880, 580, 1030, 400, 760, 570, 650, 1050, 560, and 910 nm as the most important for identifying heavy element-contaminated plants. Finally, the K-means method showed high accuracy (R2 = 0.89) for identifying and classifying plant organs affected by pollution from healthy parts. It is worth noting that the investigation of the contamination of Rosmarinus officinalis with heavy elements using electromagnetic waves represents a novel contribution to the field, particularly given the importance of this plant in the pharmaceutical and food industries.

Using machine learning to predict processes and morphometric features of watershed.

The research aims to classify alluvial fans' morphometric properties using the SOM algorithm. It also determines the relationship between morphometric characteristics and erosion rate and lithology using the GMDH algorithm. For this purpose, alluvial fans of 4 watersheds in Iran are extracted semi-automatically using GIS and digital elevation model (DEM) analysis. The relationships between 25 morphometric features of these watersheds, the amount of erosion, and formation material are investigated using the self-organizing map (SOM) method. Principal component analysis (PCA), Greedy, Best first, Genetic search, Random search as feature selection algorithms are used to select the most important parameters affecting erosion and formation material. The group method of data handling (GMDH) algorithm is employed to predict erosion and formation material based on morphometries. The results indicated that the semi-automatic method in GIS could detect alluvial fans. The SOM algorithm determined that the morphometric factors affecting the formation material were fan length, minimum height of fan, and minimum fan slope. The main factors affecting erosion were fan area (Af) and minimum fan height (Hmin-f). The feature selection algorithm identified (Hmin-f), maximum fan height (Hmax-f), minimum fan slope, and fan length (Lf) to be the morphometries most important for determining formation material, and basin area, fan area, (Hmax-f) and compactness coefficient (Cirb) were the most important characteristics for determining erosion rates. The GMDH algorithm predicted the fan formation materials and rates of erosion with high accuracy (R2 = 0.94, R2 = 0.87).

An applicability test of the conventional and neural network methods to map the overall water quality of the Caspian Sea.

This study investigates the water quality of the Caspian Sea by examining the presence of nutrients and heavy metals in the water. Water samples were collected from 22 stations and analyzed for nutrient and heavy metal levels. The study used the fuzzy method to prepare water quality maps and employed ANNs methods to predict microbial contamination for future years. The results revealed that the western and northwestern parts of the region had higher nutrient levels (about 40.2 % of the region), while the eastern and northeastern shores were highly polluted due to increased urbanization (about 70.1 % of the region). The long short-term memory (LSTM) method was found to have the highest accuracy compared to other ANNs methods and indicated a recent increase in pollution (RWater quality2=0.940, ROECD2=0.950, RTRIX2=0.840). The study recommends targeted research to identify the causes and means of controlling pollution in light of the predicted increase in pollution in the Caspian Sea.

Multi-criteria decision analysis integrated with GIS to determine land suitability for cultivation and best harvest time of vine.

BACKGROUND: In this study, the quality of land suitability for vine cultivation in south-western Iran was evaluated and a land suitability map for vine cultivation was developed using the fuzzy-analytic hierarchy process (AHP). The best harvest time of vines was determined based on the relationship between total soluble solids (TSS) and titratable acidity (TA) with fruit colour (red, green, and blue or RGB) in ten points and also the growing degree-days (GDD) maps from April to December. The relationship between GDD and effective parameters in vine cultivation was determined using principal component analysis (PCA) and Pearson correlation methods. RESULTS: The results illustrated that the maximum temperature and relative humidity (RH) have the greatest effect on vine cultivation and its yield (weight 0.24). The results of the land suitability map showed that central regions have better conditions for growing vines (32%). The measurements of TA and TSS depicted that vines of the northern parts have higher TA and lower TSS and there is a significant relationship between them and fruit colour. The results of GDD maps showed that the harvest time of ruby vine and Gezel-azm is July and August, respectively. Also, the temperature (Tmean , Tmax and Tmin ), wind speed, and GDD were the most important parameters to determine the best location for vine cultivation. CONCLUSION: Determining land suitability for cultivation, the best harvest time, the time of grape ripening, and following the exact time of export and import of vine has a vital role to increase its productivity and services. © 2022 Society of Chemical Industry.

Fuzzy AHP-based spatial distribution of fig tree cultivation in Zaprionus indianus infection risk for sustainable agriculture development.

The spatial distribution of fig trees infected by Zaprionus indianus (ZI) disease, an invasive pest, was analyzed as a control solution to determine the prone area of their growth and cultivation prevention in Southwest Iran. With this aim, the study presented the use of 9 suitability variables for fig tree cultivation mapping in 3 main steps: (i) pre-processing data of each input variable with fuzzy membership function, (ii) land suitability mapping (LSM) by using the pair-wise comparison matrix of analytical hierarchy process (AHP) method and Geographical Information System (GIS) technique, (iii) exclusion layers of Zaprionus indianus from the temperature data and growing degree days (GDD) (from April to October) with the support of inverse distance weighting (IDW) method. The results show that the central regions and parts of the east and northwest of the region (16%) are more suitable for fig cultivation. Compared to 7 growth periods, the insect is more active in the southern parts of the region than in the northern parts. Therefore, it is possible to cultivate figs with high yield in parts of the region where the land is suitable for growing this crop with the lowest activity of ZI. The overlay results show that the suitability distribution of fig cultivation in high and very high levels is mainly in the central regions (13,300 km2, 10%), parts of the east (5320 km2, 4%), and northwest (2660 km2, 2%) of the region. The proposed approach can be useful for management, planners, and local people in the development of agricultural production areas.

A hybrid GIS-MCDM approach for multi-level risk assessment and corresponding effective criteria in optimal solar power plant.

This study aims to propose a hybrid method for suitability assessment with different risk levels to construct solar power plants (CSPPs) in southern Iran. The fuzzy-analytic hierarchy process (AHP) and fuzzy were applied to forecast and determine the suitable location for CSPPs. To extract suitable location maps with different risk levels for CSPPs, ordered weighted averaging (OWA) was implemented. In addition, the best subset regression method was used to determine the most effective factors in CSPPs. Based on the results of the fuzzy-AHP method, 42% of the southern regions of the area was suitable for CSPPs. Based on the results of the OWA method, the most suitable areas were located in the north and south in all of the risk areas with increasing values. The results demonstrated that the FCM and sub-clustering approaches can accurately predict land suitability classes (LSCs) for CSPPs. Moreover, the best subsets regression (BSR) results showed that distance to power transmission line (PTL) and temperature exhibited the strongest correlation. Finally, receiver operating characteristics (ROC) were used to determine the accuracy of these methods. The results showed that the area under the curve (AUC) values were highly accurate (AUCFuzzy-AHP = 85.0%, AUCOWA = 83.0%).

Investigation of land use changes in rural areas using MCDM and CA-Markov chain and their effects on water quality and soil fertility in south of Iran.

The purpose of the study is to predict drought changes in Dariun, Fars Province, and their impact on water and soil quality. To prepare drought, water, and soil quality zoning maps, Landsat satellite images and the kriging method were used. The fuzzy maps and weights for each parameter were then determined using fuzzy and analytic hierarchy process (AHP) methods. Additionally, cellular automata (CA)-Markov chains were used in order to predict the impact of drought changes on water and soil quality. Using the fuzzy-AHP method, water quality and soil fertility in 2020 were lower compared to previous years, mainly because of land use changes that increased pollution. Based on results of the Markov and CA-Markov chains, approximately 31% of the region will have very poor levels of soil fertility and water quality in 2050. Further, based on remote sensing indicators, it is determined that about 25% of the region will be at high risk of drought in 2050. Thus, if adequate management of the region is not done, the possibility of living in these areas may diminish in the coming years due to drought and deteriorated water and soil quality.

A multi-criteria GIS-based model for wind farm site selection with the least impact on environmental pollution using the OWA-ANP method.

Wind energy is considered one of the most efficient and cost-effective ways to generate electricity, since it has a low environmental impact. So, it is essential to identify the best places to build wind farms that have the lowest impact on human health and the highest performance. In order to determine the appropriate locations for the construction of wind power plants, in the study first, the interpolation maps of the most important parameters for the construction of wind power plants were created. Then, using the analytic network process (ANP) method due to higher accuracy than other weighting methods (the two-by-two comparison of external and internal data), the weight of each criterion was determined by establishing the external and internal relationships between the criteria and sub-criteria. In this study, since the objective was to prepare land suitability maps with different levels of risk in order to further manage the area, the OWA method was used to prepare land suitability maps. Based on the results of the ANP method for weighing each parameter, wind speed and protected areas were the most and least important parameters to build the power plant. According to the results of the OWA method, 0.78 and 0.1% of the area were suitable for building power plants at high and low risk levels, respectively. The study also found that the number of wind turbines that can be built in the region at both high and low risk levels was 422 and 75, respectively. Using the buffer function, the number of turbines for the construction of high-risk power plants was reduced to 284 by using the appropriate distance from residential areas. The ANP and OWA methods were used to prepare several maps for the evaluation of land suitability with different levels of risk, one of which could be used for the construction of a power plant.

Investigation of water quality and its spatial distribution in the Kor River basin, Fars province, Iran.

As one of the largest rivers in the southwest of Iran, the Kor River plays an important role in local economy and ecosystem. However, the rapid development of industry has caused significant pollution in this river in recent years. Despite of a number of studies reported on this river regarding water pollution, few have conducted a comprehensive investigation of a wide range of water quality parameters to map the current pollution status. This study focuses on 21 water quality parameters around the industrial centers of the Kor River basin with samples taken from 25 stations. With the measured parameters, the interpolation maps of each parameter were determined using the Kriging method, and the water quality was quantified using the Water Quality Index (WQI) method. The results showed that the WQI values were between 28 and 73, showing more pollution around the factories than in the upstream areas. The results of the principal component analysis (PCA) indicated that BOD, COD, NO3-, and coliforms were the most important parameters among the 21 parameters affecting the water quality. Linear regression results suggested that the best parameters for determining coliforms and WQI values were BOD, and Cr, PO43-, Hg and Zn levels, respectively, with R2 greater than 0.87. These results can also simplify the prediction of coliforms and WQI using only a few parameters. We further found that flatter regions generally had more pollution, primarily due to pollutant accumulation as a result of water stagnation.

Assessment of risk of non-cancer disease in contaminated plant (Ocimum basilicum L.) and soil.

This study tried to conduct an investigation into the rate of contamination by heavy metals (HMs) in both the soil used in the plantation of the basil (Ocimum basilicum L.) as well as the plant itself. The proposed methodology works by assessing the concentrations of 4 heavy metals, inclusive of Pb, Zn, Ni, and Cd. The target hazard quotient (THQ) and the bioconcentration factor (BCF) were deployed for assessing the rate of contamination by HMs within the plant. The plant samples were also analyzed at different stages of growth (DSG) through inspection of their reaction to electromagnetic waves (EW). The results indicated that the THQ was substantially high for Pb and Zn, indicative of the high contamination of the study samples by the metals thereof. The hazard index (HI) for non-carcinogenic hazards was also measured for the entire HMs at 46.64, denoting a high level of contamination in the basil. BCF results also indicated Cd as the most absorbed contaminant (BCF = 1.88) by the target plant. The optimal vegetation index for assessment of HM contamination in the target plant, on the report of the findings, was identified as PD312. Therefore, utilizing EW, the reaction of contaminated plants in DSG is forecastable.

Effects of heavy metal contamination released by petrochemical plants on marine life and water quality of coastal areas.

The present study attempts to assess the threat of water contamination in Persian Gulf by heavy metals (Fe, Cr, Pb, Cu, Zn, Cd, Se, and Ni) and its subsequent effects on five fish species including Scomberomorus guttatus (S. guttatus), Lethrinus nebulosus (L. nebulosus), Brachirus orientalis (B. orientalis), Pomadasys kaakan (P. kaakan), and Scomberomorus commerson (S. commerson). Water and fish samples from fourteen monitoring stations were obtained to determine the concentrations of contaminants in water and fish. Heavy metal pollution index (HMPI) and non-carcinogenic hazard quotient (NHQI) were employed to evaluate contamination level in water and fish muscle. The Kriging geostatistical method was employed to determine the spatial distribution of different heavy metals around petrochemical plants. The highest NHQI values for P. kaakan and B. orientalis species were 1.036 and 1.046, respectively. In both cases, the NHQI values were higher than the maximum allowable value of 1, indicating that both fish species were on the verge of contamination by heavy metals, which in turn makes the consumption of these fish highly hazardous to human health. The lowest NHQI value was observed in S. commerson species at a value of 0.394, indicating its harmlessness to human health. Overall, fish species living within the top 5 m of the water column (S. commerson and S. guttatus) were found to be less contaminated by heavy metals compared to species dwelling near the seafloor (P. kaakan and B. orientalis). Results also indicated the pollution absorption rate in S. commerson and S. guttatus were 0.45 and 3.4 mg/kg-year, while the corresponding values for the B. orientalis and L. nebulosus species were 6 and 2 mg/kg-year, respectively. P. kaakan species showed a pollution absorption rate of 3.2 mg/kg-year. High heavy metal concentrations of 4.8, 10, 9.8, 5.2, 9.4, and 6.7 mg/L were obtained for Cr, Zn, Pb, Ni, Fe, Cu, and Cd, respectively, in water samples obtained from stations nearby petrochemical plants. The HMPI index for the most contaminated stations was ten times that of the maximum allowable limit. Given the intense activity of oil, gas, and petrochemical plants in the Persian Gulf, defining safe fishing areas by management practices similar to contamination zoning maps presented in this study can substantially protect the public health from heavy metal contamination.

Determining and forecasting drought susceptibility in southwestern Iran using multi-criteria decision-making (MCDM) coupled with CA-Markov model.

Forecasting drought and determining relevant data to predict drought are an important topic for decision-makers and planners. It is critical to predicting drought in the south of Fars province, an important agricultural center in Iran located in arid and semi-arid climates. The purpose of this study was to generate a drought map in 2019 using 12 parameters: altitude, aridity index, erosion, groundwater depth, land use, PET (Potential evapotranspiration), precipitation days, precipitation, slope, soil texture, soil salinity, and distance to river, and predict drought maps in 2030 and 2040 using the cellular automata (CA)-Markov model spatially. The fuzzy method was first used to homogenize the data. Next, by evaluating each parameter, the weight of each parameter was calculated using the analytic hierarchy process (AHP), and a map of drought-prone areas was generated. The results of the fuzzy-AHP method showed that the eastern and southeastern regions of the study area were prone to drought. The four most predictive parameters in causing drought, i.e., aridity index, PET, precipitation, and soil texture, were selected using the Best search method and were then chosen as the input to determine drought mapping using the fuzzy and AHP methods. Finally, the CA-Markov model was used to predict future drought maps, and the results showed that in 2030 and 2040 the drought situation in the east and south of the study area would intensify.

Investigation of plant contamination to Ni, Pb, Zn, and Cd and its relationship with spectral reflections.

This study aims to investigate the toxicity of the plant to heavy elements (HMs). For this purpose, the estimated daily intake (EDI) parameters of potentially toxic elements (PTE) per kilogram of body weight, target hazard quotient (THQ) for non-carcinogenic disorders, total hazard index (HI), and bioconcentration factor (BCF) are determined in the plant at different stages of growth. In this study, the reaction of the plant to different electromagnetic waves at different stages of growth (DSG) is also investigated, and the relationship between the THQ values and electromagnetic waves is prepared. The results show that Pb has the highest EDI value (5.97), Pb (74.67) and Cd (9.75) have the highest THQ values, and Cd has the highest BCF value (30.44). Also, the results show that HI values are higher than the threshold in the growth (69.98), flowering (71.38), and fruiting (68.06) stages. Results of BCF indicate Pb, and Cd has absorption rate in Capsicum towards. Contaminated Capsicum plants submitted to electromagnetic waves showed a significant relationship between Pb and the b490, and b560 spectra, Cd and Ni the b450 spectrum, and Zn the b460 spectrum. This finding highlights the salience of employing electromagnetic waves in assessing contamination in plants. Put differently, THQ can be estimated using electromagnetic waves without any need for laboratory studies.

Ecological risk potential assessment of heavy metal contaminated soils in Ophiolitic formations.

The purpose of this study is to generate maps of contamination risk for cadmium (Cd), copper (Cu), lead (Pb), nickel (Ni), and zinc (Zn) in soils of a large alluvial fan located in Neyriz, Iran and to investigate their possible entry into the food chain. To this aim, the concentrations of the heavy metals of the soils are measured. The Geo-accumulation index (Igeo), Muller index, and potential ecological risk index are then used to evaluate soil contamination. The spatial distribution map of elements is also prepared using the kriging method. The results show that the Cd concentration in soils (mean 23 mg/kg) is 10-40 times higher than the global standard threshold (0.30-0.70 mg/kg), the Ni concentration (mean 13 mg/kg) is lower than the threshold (34 -12 mg/kg), the Cu concentration (mean 19.39 mg/kg) is below the threshold (24-13 mg/kg), the Zn concentration (mean 14.11 mg/kg) is also below the threshold (45-100 mg/kg), and the Pb concentration (mean 93.78 mg/kg) is higher than the threshold (44-22 mg/kg). The accumulation index values for Pb and Cd are 1.61 and 5.3, respectively, which decrease from the top to bottom of the study area. The enrichment factor values for Cu, Zn, Pb, Cd, and Ni are 0.43, 0.14, 4.60, 62.57, and 0.27, respectively, which also decrease from top to bottom. The accumulation index values in the soils confirm the occurrence of contamination and further indicate that the elements in the soils originated from local materials and Ophiolitic formations masses in the area. Overall, this research for the first time investigates the effect of natural factors (geological formation) on the soil and plant pollution in the study area and shows that, in addition to pollution by human activity, natural factors such as type of formation can lead to soil and plant pollution.

Assessment of heavy metals contamination and the risk of non-cancerous diseases in vegetable using electromagnetic-chemical.

This study seeks to assess the reaction of the eggplant (Solanum melongena L.) to soil samples contaminated. Following, cultivation, growth, and harvest, the plant samples were prepared and maximum absorption rates of heavy metals were measured in both leaf and fruit. The estimated daily intake (EDI), the target hazard quotient (THQ), and the bio-concentration factor (BCF) were measured at various intervals during the growth period of the plant. Spectral analysis was also performed to assess the reaction of target crops to heavy metals. The results showed that in the second and third stages of plant growth, the THQ values were more than 1 for infected plants with Cd, Pb, and Zn. According to results from the BCF analysis, the absorption rate in Pb, during the growth stages was relatively high, in crops contaminated by Ni was around 1 in the second and third stages, and in plants contaminated by Cd was extremely high. All crops contaminated by heavy metals showed higher reflection rates in the 400-500 and 600-700 nm range. So, using electromagnetic waves during different stages of growth, the reaction of eggplant cultivated in soil samples contaminated by heavy metals is predictable.

Determination of the optimal location for constructing solar photovoltaic farms based on multi-criteria decision system and Dempster-Shafer theory.

Considering environmental concerns regarding air pollution which is induced by burning fossil fuels to generate electrical power, utilizing solar energy as a green and sustainable energy source is of great interest. This study proposes a novel framework to determine the optimal location for constructing solar photovoltaic (PV) farms. To locate the suitable areas for PV farms, firstly, a fuzzy-based method is utilized to homogenize the input parameters, thereafter, the analytical hierarchy process (AHP) and Dempster-Shafer (DS) methods are independently used. In the AHP method, the proper weight for each input parameter is generated utilizing a pairwise comparison matrix. However, the DS method identifies output in different confident levels. Finally, southeast of Fars province in Iran as a region with high sunny hours in the year is selected, and the applicability of proposed methods is examined. The results show that 32% of the case study is located at high and good suitability classes in the fuzzy_AHP method. However, it is 18.56%, 16.70%, 16.32% according to 95%, 99% and 99.5% confident levels in the fuzzy_DS method, respectively. Comparisons of the fuzzy_AHP and fuzzy_DS methods at 20 points with various solar radiation intensities and the number of dusty days parameters indicate that the fuzzy_DS method can more reliably determine the optimal PV farm locations. Additionally, as the fuzzy_DS method determines the optimal locations with different confident levels, this method can benefit decision-makers to determine the risks associated with selecting a specific site for constructing solar PV farms.

Using adaptive neuro-fuzzy inference system and multiple linear regression to estimate orange taste.

In this research, some characteristic qualities of orange fruits such as vitamin C and acid content; weight; fruit and skin diameter; and red (R), green (G), and blue (B) values of the RGB color model for 70 samples were used to predict the taste of orange grown in Darab, southeast of Fars Province, Iran, by multiple linear regression (MLR) and adaptive neuro-fuzzy inference system (ANFIS). To use MLR, firstly the most important input data were selected, and then, the best model to predict the taste of orange was applied. In this research, methodology of ANFIS consisted of selection of dependent orange taste, fuzzification, fuzzy inference rule, membership function, and defuzzification process. The predictive capability of these models was evaluated by various descriptive statistical indicators such as mean square error (MSE) and determination coefficient (R 2). The results showed that the prediction performance of the MLR model has a strong significant relationship between orange taste and vitamin C (0.897**), red color (0.901**), and blue color (0.713*). Also, the results of ANFIS model showed that with low error for train and check data increased the most accuracy for prediction of orange taste. Moreover, the results indicated that the success rate of taste determination for orange is higher by using ANFIS compared to the MLR. This research was to provide valuable information for orange taste.