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.
Mohammad Reza Gili; Davoud Ashourloo; Hossein Aghighi; Ali Akbar Matkan; Alireza Shakiba
Abstract
Changes in crop growth at relatively short intervals, asymmetry of cultivation of similar crops, the spectral similarity between different crops at certain times of the growing season, and lack of ground data make classifying crops in satellite imagery a challenging task. Changing the amount of canopy ...
Read More
Changes in crop growth at relatively short intervals, asymmetry of cultivation of similar crops, the spectral similarity between different crops at certain times of the growing season, and lack of ground data make classifying crops in satellite imagery a challenging task. Changing the amount of canopy and greenness during the growing season is one of the most prominent characteristics of vegetation, including agricultural products, which can be monitored by using time series of vegetation indices that have useful information about the sequence of phenological features of crops. The use of deep learning methods with the ability of learning sequential information obtained from these time series can be useful in crop mapping and reducing dependence on ground data. The LSTM network is one of the types of RNNs in sequential data analysis that has the ability to learn long-term sequences of time-series information. Therefore, in this study, after extracting the NDVI time-series of 9 different dates from Sentinel-2 satellite images for a region located in Moghan plain, with ground labeled data related to the type of crops cultivated, we trained a convolutional LSTM network. Then we used this trained network to classify agricultural products in another region of the plain as a test site, and achieved an overall accuracy of 82% and a kappa coefficient of 0.8. Increasing the number of ground samples and selecting the exact boundary of crops, can increase the efficiency of the method used.
Davoud Ashourloo; Hamid Salehi Shahrabi; Hamed Nematollahi
Abstract
Spectral vegetation indices have been used as a useful tool in remote sensing to estimate the yield of agricultural crops. However, one factor, which reduces the capability of indices for crop yield estimation, is the limited number of available satellite images. Furthermore, in cases when there are ...
Read More
Spectral vegetation indices have been used as a useful tool in remote sensing to estimate the yield of agricultural crops. However, one factor, which reduces the capability of indices for crop yield estimation, is the limited number of available satellite images. Furthermore, in cases when there are not enough Landsat images, the capabilities of spectral indices in yield estimation using a fusion of MODIS and Landsat data, have been less investigated. The aim of this paper is, first, to introduce the most efficient index/indices for estimating the canola yield and, second, to try to use data fusion techniques in order to increase the efficiency of the selected index/indices. Due to flowering in the growth period, canola has special spectral features. In this research, to estimate the yield of canola, a yield database along with the time series of the Landsat and MODIS data of Moghan Agro-Industry Company fields were provided. Then, 10 spectral indices were evaluated for estimating the canola yield. The relations between the canola yield and the candidate indices were investigated and it was revealed that, during the flowering period, the NDYI index obtained a higher accuracy compared with other indices (r = 0.73). The fusion of the Landsat and MODIS time series data based on Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM), resulted in a 7%-increase and an 11%-decrease in correlation and RMSE (kg/ha), respectively. This research indicated that data fusion techniques are able to improve the performance of spectral indices and hence increase the accuracy of crop yield estimation.
Hamed nematollahi; Davoud Ashourloo; Abas Alimohammadi; Elham Khodabandehloo; Soheil Radiom
Volume 10, Issue 3 , January 2019, , Pages 105-122
Abstract
One of important objectives in sustainable agriculture is preservation of healthy ecosystems with focus on natural aquatic and terrestrial resources management in order to accomplish food security at local and global scales. Time-series remotely sensed datasets are precious and valuable resource of temporal ...
Read More
One of important objectives in sustainable agriculture is preservation of healthy ecosystems with focus on natural aquatic and terrestrial resources management in order to accomplish food security at local and global scales. Time-series remotely sensed datasets are precious and valuable resource of temporal and spectral information that could support researchers to access field management goals. Farm management have been always encountered some challenges such as lack of access to quantitative and qualitative information of agricultural crops. This research aims to develop crop and field condition indices using time-series of NDVI (Sentinel-2) and crop type maps of Moghan Agro-Industry (MAI) in 2016-2017 and also Shahid Rajaei Agro-Industry (SRAI) in 2017-2018. Then we tried to identify parts of the fields that are affected by Environmental factors such as disease, pest, weed, soil-related deficiencies and uneven distribution of water due to Inefficient irrigation system. To this end, Time-series of NDVI for four crops (wheat, maize, alfalfa and sugar beet) in various fields was provided. Finaly, field and crop condition indices were developed to show the variations of crop in each field and also the fields in comparison with each other. Finally, the proposed indices showed high accuracy with ground observations. The results were 88.88% for Alfalfa fields in MAI, and 94.11% for wheat fields in SRAI. After evaluation of the results of indices with ground observations, it was revealed that where field (homogeneity) index is low, growth limiting factors are activated.
D Ashourloo; H Aghighi; A.A Matkan; H Nematollahi
Volume 9, Issue 4 , May 2017, , Pages 111-128
Abstract
Wheat rust is one of the important diseases of cereal crops in Iran and other countries in the world which imposes irreparable damages to the agricultural economy. In this study, the effects of the leaf and yellow rust disease on wheat leaves reflectance were studied. For this purpose, various vegetation ...
Read More
Wheat rust is one of the important diseases of cereal crops in Iran and other countries in the world which imposes irreparable damages to the agricultural economy. In this study, the effects of the leaf and yellow rust disease on wheat leaves reflectance were studied. For this purpose, various vegetation indices derived from leaf spectra were measured. To do this, diseases ratio and varying degrees of disease were extracted by using digital camera and multi-step algorithm including color Transformation, mask preparation, texture and maximum likelihood classification. Results show variation in the values of the parameters with changing in proportion of disease whereas the data scattering of indexes Increase quickly. The highest correlation was for the NDVI (0.9) and the minimum was for the red slope (0.2). With the similarity criteria, range and inter-class scattering relations of spectra and disease were studied and with Increasing of the disease ratio. These criteria are altered by developing of disease ratio .Further investigation showed, spectrum mixing in different fraction of yellow, orange, brown and dead is a cause for data scattering with disease development.