Salman Goodarzdashti; Mohamad Seifi; Mahshid Kohandel; Davoud Ashourloo; Hossein Aghighi
Abstract
Potatoes are the fourth most cultivated crop worldwide. Regarding the strategic role of this crop in food security, accurate potato mapping provides essential information for national crop censuses and potato yield estimation /prediction at any scale. Although remote sensing (RS) approaches based on ...
Read More
Potatoes are the fourth most cultivated crop worldwide. Regarding the strategic role of this crop in food security, accurate potato mapping provides essential information for national crop censuses and potato yield estimation /prediction at any scale. Although remote sensing (RS) approaches based on optical and/or microwave sensors have been widely employed to monitor cultivated land (including crop area, type, condition, and yield forecasting), the identification of potato planting areas using RS data has not been much addressed. Hence this study addresses the literature gap by suggesting an effective potato mapping approach that uses the time series of the Sentinel-2 (S2) images, Google Earth Engine (GEE) platform and machine learning methods. Since most crops have specific spectral and temporal characteristics during the growing season, this research has presented a method to discriminate potato fields from other crops using time series images without explicit thresholding. We employed 1648 ground truth data to optimize, train, and evaluate the model at the study site, which includes potatoes and other fields. A handheld GPS receiver was used to collect these data. The performance of this approach is evaluated by conducting a set of experiments in Hamedan and Bahar cities, as the regions grow more potatoes than any other places in Iran. Accurate identification of potato fields was completed by extracting the required features, namely the potato phenology feature and NDVI medians, from the time series of the S2 satellite bands. After that, these features were utilized as the input parameters to Support Vector Machine (SVM) technique. In order to train the most optimal SVM model using RBF kernel, Gamma and C values were optimized with the help of the 5-fold cross-validation method. These values were then employed during the algorithm's implementation on GEE platform. The estimated overall accuracy and Kappa coefficient are 90.9% and 0.82 for Hamedan and 93.3% and 0.87 for Bahar, respectively. The results of this research indicate the efficiency of SVM technique in potato acreage mapping. Moreover, the selected features such as potato phenology feature can be considered as discriminating features for improved identifying of crop farms.
Reza Shahhoseini; Kamal Azizi; Arastou Zarei; Fatemeh Moradi
Abstract
Land use maps describe the spatial distribution of natural resources, cultural landscapes, and human settlements that are essential for decision-makers. Therefore, the accuracy of maps obtained from the classification of satellite images is very effective in uncertainty for urban management. Due to the ...
Read More
Land use maps describe the spatial distribution of natural resources, cultural landscapes, and human settlements that are essential for decision-makers. Therefore, the accuracy of maps obtained from the classification of satellite images is very effective in uncertainty for urban management. Due to the uniform quality of images in large areas at regular intervals, remote sensing images are essential for land use maps. The primary purpose of this study is to present a proposed method to create an accurate land cover map in urban areas using a combination of Sentinel-1 and Sentinel-2 data. For this purpose, the features of the backscattering coefficient VV and the two parameters obtained from the H-α decomposition method (entropy, alpha) of Sentinel-1 radar images and the features of the blue, green, red band, NDVI, NDWI, MNDWI, and SWI were extracted from Sentinel-2 Multispectral images and used as influential components to classify the urban area. To separate agricultural areas from other coatings, the SWI index was used. Elevation data have also been used to optimally distinguish complex classes with different topographies. We evaluated the extraction of effective indicators from these two datasets in an object-oriented approach based on support vector machine algorithms and random forest for land use classification. The results showed that using properties extracted from radar and Multispectral images simultaneously in the object-oriented classification method could altogether determinate the object's properties in the study area. When optical and radar data were used simultaneously for both classification algorithms, the overall accuracy classification increased. For the stochastic forest method, which provided the highest accuracy, the overall accuracy for the radar and optics data combination approach increased by 13% and 5%, respectively, compared to the radar feature approach and the optics feature approach alone. There was also a significant difference in classification accuracy at all levels between the support vector machine classification algorithm and the random forest. The results showed that the random forest classification method's overall accuracy and support vector machines were 83.3 and 79.8%, respectively, and the kappa coefficient was 0.72 and 0.68%, respectively.
Seyed Ahmad Mousavi; milad janalipour; Nadia Abbaszadeh Tehrani
Abstract
The basis for proper planning and management is to have accurate and timely statistics and information. One of the most important statistics of the agricultural sector is the annual production rate of each crop, which also depends on the area under cultivation of crop and its efficiency. One of the tools ...
Read More
The basis for proper planning and management is to have accurate and timely statistics and information. One of the most important statistics of the agricultural sector is the annual production rate of each crop, which also depends on the area under cultivation of crop and its efficiency. One of the tools that can calculate the area under cultivation in the least time, with low cost and with high accuracy is remote sensing science and technology. In this study, two classification methods including artificial neural networks and support vector machine with different kernels are used and the area under cultivation of major crops in the region consisting of 8 classes is estimated. According to the results, the overall accuracy of the artificial neural networks and support vector machine was 97.74% and 97.96% with a kappa coefficient of 0.97 for both methods, indicating that both methods are good for separation and classification of agricultural lands in the area. Based on the overall accuracy, it can be concluded that the two methods of classification have almost the same results in the region. Also, based on the results of the user's accuracy for the four crops including Alfalfa, Rice, Onion and Melon, the support vector machine method performs better than the neural network method and also for dry and water Wheat, Sorghum, and Pasture, the neural network method out performs the support vector machine in the region.
Zeinab Ghodsi; Mir Masoud Kheirkhah Zarkesh; Bagher Ghermezcheshmeh
Abstract
Land-cover/land-use maps are necessary for monitoring land changes and proper planning for managers in agriculture, natural resources and environment fields each year. The method of field data collection using GPS and land survey is time-consuming and costly. Therefore satellite images which have entire ...
Read More
Land-cover/land-use maps are necessary for monitoring land changes and proper planning for managers in agriculture, natural resources and environment fields each year. The method of field data collection using GPS and land survey is time-consuming and costly. Therefore satellite images which have entire coverage and repetition of collection, low cost and real-time data, are usually used so that land-cover/land-use maps are produced. Accurate mapping using technique suitable for today is a key factor. Although in the past, conventional classification methods have been applied to images such as Landsat, using new satellite images and modern classifiers specially machine learning has been growing recently and their effectiveness in preparing land-cover/land-use maps has been very successful. Another advantage of satellite images is repetitious collection and according to that, vegetation changes through time can be used to differentiate land cover types. The Sentinel-2 satellite with the superiority of a pixel rating of 10 meters is one of the appropriate tools to discriminate land cover types. In the current study, Support Vector Machine and Random Forest classifiers on multi-temporal Sentinel-2 images were used to differentiate land use and crop types of Sanjabi plain in Ravansar and their accuracies were compared. To do so, after sampling, Principal Component Analysis was performed for four dates in crops’ growing season and PC1,2,3 bands of the images were combined. The two techniques were implemented on the layerstacks of PC1,2,3 bands of the images and the training samples. Results of accuracy assessments showed that Support Vector Machine, with overall accuracy of 91.36% and Kappa coefficient of 0.8927, produces a more precise land use and crop map rather than Random Forest method.
I Yoosefdoo; A Khashei Siuki
Volume 9, Issue 2 , December 2017, , Pages 99-116
Abstract
The use of groundwater plays an important rule for agricultural and drinking water purposes in the north of Iran especially in Koochesfehan region. In these areas, the excessive use of chemical fertilizers, especially nitrogen based ones, beside the inadequacy in the treatment and release of urban and ...
Read More
The use of groundwater plays an important rule for agricultural and drinking water purposes in the north of Iran especially in Koochesfehan region. In these areas, the excessive use of chemical fertilizers, especially nitrogen based ones, beside the inadequacy in the treatment and release of urban and industrial wastewater are some of the most effective parameter in groundwater pollution, especially about the concentration of nitrate. Therefore, identification and mapping of vulnerable aquifer areas, i.e. areas where pollutants can be penetrated and discharged from the ground surface to the groundwater system, is an appropriate management tool for preventing the pollution of groundwater resources. In this study, with the purpose of identifying vulnerable aquifers and areas with high nitrate content as the main vulnerability areas, by using 7 variables the Drastic method and by using the Aller weighing criterion, vulnerability index of the region was estimated. Then, by comparing the vulnerability index and the amount of nitrate measured in the zoned area, the correlation between nitrate and Drastic vulnerability index was calculated. The results showed that the vulnerability of the Astaneh-Koushfahan plain aquifer is located in four areas: 56.16% of the plain has a low vulnerability, 51.29% has a low to moderate vulnerability, 28.46% has a moderate to high vulnerability, 67.1% is vulnerable. It is too much. The correlation between the Drastic (vulnerability) index and the concentration of nitrate was 80%, which confirmed that nitrate was the main cause of vulnerability in this the aquifer. So, finding a method for estimating the amount of nitrate in present and future in this area with high speed and precision was assumed as the goal of this study. The amoun of nitrate were estimated with four artificial intelligence methods: artificial neural network, fuzzy model, support vector model and fuzzy-neural network. For this purpose, the seven Drastic variables data assumed as input parameters and the measured nitrate content in 30 different wells of the area were zoned by use of GIS software and divided into two categories of training and experimentation and they give as output parameters to all data-driven models. The results showed that all used artificial intelligence models give a good estimation of the amount of nitrate, but the neural network model had the best results, so that there was a correlation of 98% between computational nitrate and observation nitrate value. Finally, by choosing the model of the neural network as the superior model, it was tried to estimate the nitrate by decreasing the input parameters. The results showed that with 5 parameters of soil environment-unsaturated medium-saturated environment -water-hydraulic and eliminating two parameters of nutrition and topography, the correlation of estimated nitrate with the actual amount of measured nitrate is 0.90.
A Shamsoddini; Sh Esmaeili
Volume 9, Issue 2 , December 2017, , Pages 117-132
Abstract
Differentiating agricultural areas which are not covered by vegetation from bare lands as well as identifying bare lands from urban areas in medium spatial resolution images, e.g. Landsat imagery, are usually difficult and erroneous tasks which lead to the inaccurate classification results. Therefore, ...
Read More
Differentiating agricultural areas which are not covered by vegetation from bare lands as well as identifying bare lands from urban areas in medium spatial resolution images, e.g. Landsat imagery, are usually difficult and erroneous tasks which lead to the inaccurate classification results. Therefore, this study aims to present a new approach to increase the accuracy of the classification. For this purpose, different scenarios were applied based on different input attributes. The input attributes comprised of spectral bands, textural attributes, i.e. grey level co-occurrence matrix (GLCM), and two types of indices including spatial and thermal attributes proposed in this study. Three classification methods, maximum likelihood (ML), artificial neural networks (ANN), and support vector machine (SVM) embedded with different kernels, were applied to examine different scenarios. The results showed that SVM algorithm embedded with Radial basis function (RBF) results in better accuracy, with overall accuracy of 98.81% and Kappa coefficient of 98.25%, when all types of input attributes were combined together. Finally, the variable importance analysis by random forest feature selection indicated that the proposed indices played an important role to execute more efficient classification by SVM.
, A.A Torahi; M FiroziNejad,; , A Abdolkhani
Volume 9, Issue 1 , October 2017, , Pages 49-62
Abstract
Obtaining more accurate and updated information about the forest area is one of the basic factors in sustainable management of this area. Acquiring this information is more beneficial in terms of time and cost through classification of remote sensing data. In this paper, Landsat8 (OLI) data from Maroons ...
Read More
Obtaining more accurate and updated information about the forest area is one of the basic factors in sustainable management of this area. Acquiring this information is more beneficial in terms of time and cost through classification of remote sensing data. In this paper, Landsat8 (OLI) data from Maroons Behbahan riparian forest that is located in Khoozestan province of Iran were used for mapping and better management of riparian forest. Preprocessing operation including radiometric and atmospheric correction was applied to the data. Supervised classification algorithms including maximum likelihood (MLC) and support vector machine (SVM) with seven and three classes were used for classification. In order to evaluate the capability of support vector machine, three categories of training data with 241, 141 and 41 numbers with four kernels of SVM (linear, radial basic function, sigmoid and polynomial) were used. The results indicate that mapping of Maroons riparian forest using Landsat images is possible and the best result was acquired using SVM –polynomial method by three classes with overall accuracy and kappa coefficient of (99/24) % and (0/97) respectively. Also, the findings showed that with reduction of number of classes from seven to three, the accuracy of classification is increased. By reducing the number of samples to moderate, significant difference in accuracy of classification was not observed, but by more reduction of samples, the accuracy of results is reduced.
