Precision Farming
M. Saadikhani; M. Maharlooei; M. A. Rostami; M. Edalat
Abstract
IntroductionRemote sensing is defined as data acquisition about an object or a phenomenon related to a geographic location without physical. The use of remote sensing data is expanding rapidly. Researchers have always been interested in accurately classifying land coverage phenomena using multispectral ...
Read More
IntroductionRemote sensing is defined as data acquisition about an object or a phenomenon related to a geographic location without physical. The use of remote sensing data is expanding rapidly. Researchers have always been interested in accurately classifying land coverage phenomena using multispectral images. One of the factors that reduces the accuracy of the classification map is the existence of uneven surfaces and high-altitude areas. The presence of high-altitude points makes it difficult for the sensors to obtain accurate reflection information from the surface of the phenomena. Radar imagery used with the digital elevation model (DEM) is effective for identifying and determining altitude phenomena. Image fusion is a technique that uses two sensors with completely different specifications and takes advantage of both of the sensors' capabilities. In this study, the feasibility of employing the fusion technique to improve the overall accuracy of classifying land coverage phenomena using time series NDVI images of Sentinel 2 satellite imagery and PALSAR radar imagery of ALOS satellite was investigated. Additionally, the results of predicted and measured areas of fields under cultivation of wheat, barley, and canola were studied.Materials and MethodsThirteen Sentinel-2 multispectral satellite images with 10-meter spatial resolution from the Bajgah region in Fars province, Iran from Nov 2018 to June 2019 were downloaded at the Level-1C processing level to classify the cultivated lands and other phenomena. Ground truth data were collected through several field visits using handheld GPS to pinpoint different phenomena in the region of study. The seven classes of distinguished land coverage and phenomena include (1) Wheat, (2) Barley, (3) Canola, (4) Tree, (5) Residential regions, (6) Soil, and (7) others. After the preprocessing operations such as radiometric and atmospheric corrections using predefined built-in algorithms recommended by other researchers in ENVI 5.3, and cropping the region of interest (ROI) from the original image, the Normalized Difference Vegetation Index (NDVI) was calculated for each image. The DEM was obtained from the PALSAR sensor radar image with the 12.5-meter spatial resolution of the ALOS satellite. After preprocessing and cropping the ROI, a binary mask of radar images was created using threshold values of altitudes between 1764 and 1799 meters above the sea level in ENVI 5.3. The NDVI time series was then composed of all 13 images and integrated with radar images using the pixel-level integration method. The purpose of this process was to remove the high-altitude points in the study area that would reduce the accuracy of the classification map. The image fusion process was also performed using ENVI 5.3. The support Vector Machine (SVM) classification method was employed to train the classifier for both fused and unfused images as suggested by other researchers.To evaluate the effectiveness of image fusion, Commission and Omission errors, and the Overall accuracy were calculated using a Confusion matrix. To study the accuracy of the estimated area under cultivation of main crops in the region versus the actual measured values of the area, regression equation and percentage of difference were calculated.Results and DiscussionVisual inspection of classified output maps shows the difference between the fused and unfused images in classifying similar classes such as buildings and structures versus regions covered with bare soil and lands under cultivation versus natural vegetation in high altitude points. Statistical metrics verified these visual evaluations. The SVM algorithm in fusion mode resulted in 98.06% accuracy and 0.97 kappa coefficient, 7.5% higher accuracy than the unfused images.As stated earlier, the similarities between the soil class (stones and rocks in the mountains) and manmade buildings and infrastructures increase omission error and misclassification in unfused image classification. The same misclassification occurred for the visually similar croplands and shallow vegetation at high altitude points. These results were consistence with previous literature that reported the same misclassification in analogous classes. The predicted area under cultivation of wheat and barley were overestimated by 3 and 1.5 percent, respectively. However, for canola, the area was underestimated by 3.5 percent.ConclusionThe main focus of this study was employing the image fusion technique and improving the classification accuracy of satellite imagery. Integration of PALSAR sensor data from ALOS radar satellite with multi-spectral imagery of Sentinel 2 satellite enhanced the classification accuracy of output maps by eliminating the high-altitude points and biases due to rocks and natural vegetation at hills and mountains. Statistical metrics such as the overall accuracy, Kappa coefficient, and commission and omission errors confirmed the visual findings of the fused vs. unfused classification maps.
S. Rahnama; M. Maharlooei; M. A. Rostami; H. Maghsoudi
Abstract
Introduction Date palm is one of the most valuable horticultural products in Iran, which includes 16% of non-oil exports to the world. Kerman province has the second rank for the cultivation area of date palm in Iran. Having information about the exact cultivated area has gained importance for further ...
Read More
Introduction Date palm is one of the most valuable horticultural products in Iran, which includes 16% of non-oil exports to the world. Kerman province has the second rank for the cultivation area of date palm in Iran. Having information about the exact cultivated area has gained importance for further decision makings. To determine the cultivated area, organizations usually use census which has the disadvantages of high cost, wasting time and labor intensive. The aim of this research was to study the feasibility of using Landsat 8 OLI images to identify and classify the area under date palm cultivation. To accomplish this purpose, four supervised classification methods were evaluated. Materials and Methods The study area was in Bam region located at 200 km southeast of Kerman province. In this research, a total of 14 images of Landsat8 OLI satellite from the study area during fall and winter were downloaded from Landsat official web page. After preliminary inspections for interested classes (Date palm gardens, Lands covered with bare soil and forage crop fields), one of the images that was taken on Jan 14, 2017, was selected for further analysis. After initial corrections and processing, 32 images of alfalfa farms, 32 images of date palm gardens and 32 images of lands covered with bare soil, were selected using GPS data points collected in study area scouting. Shape files of all selected fields were created and utilized for supervised classification training set. The same process was also done for the unsupervised classification method. To evaluate the classification methods confusion matrix and Kappa coefficient were used to determine the true and miss-classified area under date palm cultivation. It is worth mentioning that these factors alone cannot identify the most powerful method for classification and they just give us a general overview to choose acceptable methods among all available methods. To identify the most powerful method among selected methods, confusion matrix and investigating the pixel transfers between classes is the crucial method. Results and Discussion Results of classifications revealed that the overall classification accuracy by using NN, MLC, SVM, MDC, and K-Means were 99.10% (kappa 0.973), 98.77% (kappa 0.975), 98.66% (kappa 0.973), 98.52% (kappa 0.97), and 52.66% (kappa 0.31) respectively. Concerning the confusion matrix in the NN method, the percentage of producer accuracy error in date palm class was 0% and in user, accuracy error was 1.44%. In the review of other methods, the lowest producer accuracy error value in date palm class obtained by NN and SVM methods was 0% and the highest producer accuracy error belonged to MLC method which was 1.35%. Checking the recognition power of other classes showed that in the soil class, the highest producer accuracy error was 2.32% by MDC method and the least one was 0.64% by MLC. For forage class, the highest producer accuracy error was calculated 37.07% by SVM and the least accurate one was 4.92% by MDC. Although the K-Means method with Kappa Coefficient of 0.31 did not have a good classification quality, concerning classes and samples, it successfully could identify date palm according to selective samples with 100% accuracy. Results of calculated date palm area using supervised classification methods versus actual area measurements showed that NN and SVM methods with the coefficient of determination (R2) of 0.9995% and 0.9986% had the highest coefficients. K-Means method with R-square of 0.9228% had a good correlation. In general, all supervised classification methods obtained acceptable results for distinguishing between date palm classes and two other classes. NN and SVM methods could successfully recognize date palm class. K-Means method also could recognize date palm class but the recognition included some errors such as dark clay soil textures which were classified as the date palm. Conclusion In general, overall accuracy and kappa Coefficient alone cannot identify the most powerful method for classifying and these methods just give us a general overview to choose an acceptable percentage of accuracy coefficients among available methods. After the initial selection, to identify the most powerful method of classification the pixel transfer calculations in a confusion matrix would be an acceptable technique.
M. Maharlooei; M. Loghavi; S. G. Bajwa; M. Berti
Abstract
Introduction Current study tries to find a new simple and practical real-time technique to estimate forage crop nutritional quality indices at field conditions. Estimating these indices help producers to have field quality variation layer to reach the goals of Precision Agriculture. Previous studies ...
Read More
Introduction Current study tries to find a new simple and practical real-time technique to estimate forage crop nutritional quality indices at field conditions. Estimating these indices help producers to have field quality variation layer to reach the goals of Precision Agriculture. Previous studies have shown that standardized shear characteristics of crop stem would be a good indicator for some nutritional quality indices. In previous studies, laboratory tests were conducted at controlled conditions of crop moisture content, stem diameter and employing standard shear test procedure. Materials and Methods In order to simulate field conditions, a two-stage study was conducted in Iran and United States. In the first stage fresh and naturally sun dried alfalfa stems were used in evaluating four levels of crop growth stage and eight loading conditions (four loading rates and two stem conditions). In order to evaluate the effectiveness of shear technique with respect to the conventional harvest method in Iran, shear tests were conducted using fixed and moving knives of a standard square hay baler (John Deere-348). Special fixtures were constructed to attach these knives to a universal testing machine (SANTAM, STM-20). Since evaluation of the suggested method with regard to other quality related factor indices such as different varieties and seeding rates, was not practically feasible in Iran in the second stage of this research, five different varieties and three seeding rates were tested in United States. In this part of the study, shear tests were conducted using modified Varner-Bratzler shear test with universal testing machine (TESTRESOURCES-311). Based on the results of loading rate and stem condition in the first stage, shear tests were carried out using loading rate of 500 mm/min and multiple stem condition. In both stages Specific Shear Energy (shear energy per stem diameter, J mm-1) were calculated using trapezoidal method. In order to compare the shear energy results with crude fiber nutritional quality indices such as Acid Detergent Fiber (ADF), Neutral Detergent Fiber (NDF) and Relative Feed Value (RFV), all alfalfa samples were analyzed using (Association of Official Agricultural Chemists) AOAC standard analytical laboratory methods. Statistical analyses were consisted of ANOVA mean comparison test at each level of factors and regression analysis to find the correlation between specific shear energy and nutritional quality indices. Results and Discussion Results of ANOVA analysis and mean comparisons showed a significant difference in specific shear energy at different levels of loading rates. The higher loading rates showed lower energy which was related to lower ability of knives to cut alfalfa stem thoroughly and shredding the stems at lower speed levels. Significant differences were found in different levels of annual growing cycle, harvest time and seeding rates. Alfalfa stem in fifth harvest year showed the highest shear energy due to higher lignification in plant stems. In the first year, harvested alfalfa stem did not have the lowest shear energy which might be due to existence of weeds in first year field. Results showed higher values of shear energy in fifth harvest of the season in comparison with the third harvest which was acceptable because of differences in plant received Degree Day in these harvest times. The lowest seeding rate (5 kg h-1) showed the highest shear energy respect to the other seeding rates. The reason for this significant difference could be due to lower competition to receive water and nutritions, also lower plant density helps the canopy to receive more sun light which causes higher lignification. Comparing the shear energy means in different varieties didn’t show significant differences which can be explained because of varieties adoptability to the region specific weather condition. The regression analysis showed good correlations between specific shear energy and crude fiber nutritional indices (ADF, NDF and RFV). The negative trends which were found in regression analyses were also reported in similar studies. Conclusion Two stage laboratory tests were conducted in order to evaluate the effect of alfalfa nutritional feed quality indices related factors on unitized shear energy. Results showed a significant difference of standardized shear energy mean at different levels of harvest time, annual growing cycle and seeding rates. The specific shear energy was not significantly different in different varieties because of varieties environmental adoptability. The unitized shear energy showed a good correlation with crude fiber related indices with similar trends in both stages of research and good agreements with previous studies.
M. Jafari; H. Mortezapour; K. Jafari Naeimi; M. Maharlooei
Abstract
Introduction Greenhouses provide a suitable environment in which all the parameters required for growing the plants can be controlled throughout the year. Greenhouse heating is one of the most important issues in productivity of a greenhouse. In many countries, heating costs in the greenhouses are very ...
Read More
Introduction Greenhouses provide a suitable environment in which all the parameters required for growing the plants can be controlled throughout the year. Greenhouse heating is one of the most important issues in productivity of a greenhouse. In many countries, heating costs in the greenhouses are very high, having almost 60-80% of the total production costs. In recent years, several studies have attempted to reduce the heating costs of the greenhouses by applying more energy efficient equipment and using the renewable energy sources as alternatives or supplementary to the fossil fuels. In the present study a novel solar greenhouse heating system equipped with a parabolic trough solar concentrator (PTC) and a flat-plate solar collector has been developed. Therefore, the aim of this paper is to investigate the performance of the proposed heating system at different working conditions. Materials and Methods The presented solar greenhouse heating system was comprised of a parabolic trough solar concentrator (PTC), a heat storage tank, a pump and a flat plate solar collector. The PTC was constructed from a polished stainless steel sheet (as the reflector) and a vacuum tube receiver. The PTC was connected to the tank by using insulated tubes and a water pump was utilized to circulate the working fluid trough the PTC and the heat exchanger installed between walls of the tank. The uncovered solar collector was located inside the greenhouse. During the sunshine time, a fraction of the total solar radiation received inside the greenhouse is absorbed by the solar collector. This rises the temperature of the working fluid inside the collector which led to density reduction and natural flow of the fluid. In other words, the collector works as a natural flow flat plate solar collector during the sunshine time. At night, when the greenhouse temperature is lower than tank temperature, the fluid flows in a reverse direction through the solar collector and the stored heat transferred from the collector surface to the greenhouse. The evaluation tests were conducted at three levels of fluid flow rate through the solar concentrator (0.44, 0.75 and 1.5 Lmin-1) and two different working modes of the heat exchanger. Results and Discussion The variation of thermal efficiency of the PTC at different flow rates has been illustrated in Fig 3. As shown, thermal efficiency increased with flow rate mainly because the fluid convection coefficient enhances with raising the velocity of the fluid inside the tubes. The heat storing process began from 9 am and the highest amounts of the stored heat during sunshine time occurred between 10 am and 2 pm. Fig 5 showed that the stored energy in the tank enhanced when the flat plate collector was employed beside the PTC. Also, increasing the fluid flow rate from 0.44 to 1.5 Lmin-1 improved the index of stored heat by 32.14%. Energy consumption during the night time was also significantly changed with flow rate and the mode of heating. Fig 7 indicated that the electrical energy consumption was lower with flat plate solar collector and it is possible to save the electrical energy by 26.67% using the flat plate collector. Bouadila et al., (2014) concluded that the electrical energy consumption reduced by 31% employing a natural convection flat plate solar collector system equipped with phase changed heat storage material for greenhouse heating. Since increasing the flow rate enhanced the thermal efficiency of the solar concentrator system and led to an improvement in stored thermal energy during the sunshine time, solar fraction increased with raising the flow rate from 0.44 to 1.5 Lmin-1. A maximum solar fraction of 66% was achieved at the highest flow rate when using the flat plate solar collector beside the PTC. Conclusion An experimental comparative study was conducted to investigate the performance of a novel solar greenhouse heating system at the different fluid flow rates and two modes of heating (with and without flat plat solar collector). The results can be summarized as follows: A maximum thermal efficiency of about 71% was achieved at the flow rate of 1.5 Lmin-1. Raising the flow rate from 0.44 to 1.5 Lmin-1 improved the index of stored heat and solar fraction by 32.14% and 21%, respectively. The highest value of solar fraction was found to be 66% at the highest flow rate when engaging the flat plate solar collector beside the PTC.
M. Maharlooei; M. Loghavi; S. M. Nassiri
Abstract
Precision Agriculture is continuously trying to address the sources and factors affecting the in-field variability and taking appropriate managerial decisions. One of the popular research focuses in the recent three decades has been on the development of new approaches to making yield variability maps. ...
Read More
Precision Agriculture is continuously trying to address the sources and factors affecting the in-field variability and taking appropriate managerial decisions. One of the popular research focuses in the recent three decades has been on the development of new approaches to making yield variability maps. Advancement in development of sensors and the importance of quality factor in high value crops has motivated scientists to investigate real-time and nondestructive testing methods. This study tried to introduce and evaluate a new approach to concurrent yield mapping and to estimate some nutritional qualitative factors of alfalfa production. In this study, yield quantity was determined by measurement of added hay slice in every hay compression cycle by employing a new star wheel and integrating its output with positioning data from Global Positioning System. To predict some nutritional quality properties, measurement of specific shear energy applied on the cutting blade and compressive energy on plunger head of a hay baler in field conditions were also evaluated. The results of statistical analysis of yield quantity measurement data showed a very good correlation between the suggested approach and yield mass (r=0.96 and R2=0.92). The results of using specific shear energy for estimation of crude fiber and cumulative index RFV with regard to field conditions were rated as acceptable. Using specific compression energy was suitable only for estimating the dry matter. None of the suggested methods was able to estimate the hay crude protein. Further investigations at more extensive variations of quality indices and alfalfa varieties are suggested.