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.
B. Sepehr; H. Mohamadi-Monavar
Abstract
Introduction One of the most important factors in agricultural production is nitrogen which has a great impact on plant growing, yield performance and plant quality production. The optimum amount of nitrogen fertilizer is varied from fields to fields. There are some time consuming and costly ways to ...
Read More
Introduction One of the most important factors in agricultural production is nitrogen which has a great impact on plant growing, yield performance and plant quality production. The optimum amount of nitrogen fertilizer is varied from fields to fields. There are some time consuming and costly ways to measure the nitrogen content of plants or soil, which are inappropriate for extended field or for a long growing season. Fast and remote optical sensors calculate greenness of plant using reflectance or absorbance of light from green leaves. Measuring chlorophyll with SPAD managed the nitrogen requirement for maize, Poinsettia and Nagoya Red. Whereas SPAD was not a suitable choice for chlorophyll measurement at the end of growing period. Therefore, GreenSeeker was applied as a non-contact to record the NDVI of tomato’s and cucumber’s leaves. The purpose of this research was the evaluation of GreenSeeker ability to estimate nitrogen requirement and then the plant health. Materials and Methods The study was performed on Matin and Nahid cultivars of tomato and cucumber, respectively. The pots were 291 and filled with 3 kg sieved soil. The bottom layer of each pot was filled with stone for better drainage. Before planting, the soil was analyzed in order to define the ingredients. All pots put in the greenhouse with polycarbonate structure in two floors. Measurements were repeated every week with SPAD and GreensSeeker and fertigation was started 50 days after planting (DAP). In order to provide other nutrient elements, all pots got Humic-acid at 37DAP and the effect was measured in 43rd DAP. Fertigation was continued until 71st DAP and first, second and third treatments were supplemented with extra fertilizer to reach the amount of fertilizer to fifth treatment. To calculate Total Nitrogen (TN), the concentrations of nitrate-N and nitrite-N are determined and added to the total Kjeldahl nitrogen. Chlorophyll meter (SPAD) and GreenSeeker optical sensor have become available for site-specific and need-based N management in greenhouse. The GS was located at 60 cm above the plant and measured the average NDVI. This sensor has red and NIR diodes which reflect and absorb the spectra in 660±15nm and 770±15nm regions, respectively. The SPAD values were recorded by inserting the middle portion of the index leaf in the slit of SPAD meter. As well as, chlorophyll meter can confirm the GreenSeeker output (NDVI). GreenSeeker is a suitable optical sensor because it is not affected by light and temperature variation or wind intensity. Statistical analyses were performed on the pooled data of both tomato and cucumber using Statistical Product and Service Solutions (SPSS). Regression equations were fitted between fertilizer and the readings recorded with different gadgets at different growth stages. Results and Discussion Chlorophyll content and NDVI of tomato and cucumber increased during the growing stages except in 71st DAP for cucumber. The percentage of total nitrogen of 1st, 2nd and 3rd treatments were further than two others because of supplementary fertilizer. According to the Kjeldahl result of cucumber, the 3rd treatment had the lowest nitrogen accumulation in fruits. In addition, chlorophyll and NDVI of cucumber almost showed the increasing correlation by fertilizer enhancement while the opposite behavior was seen for tomato. That would be related to different fertilizer needs of them. The linear regression of fertilizer and reading NDVI of 2nd to 5th treatments were ascending. The number of increasing leaves was calculated in all pots every weeks as another studied element. Each pot had new grown leaves every weeks that was more or sometimes less than last weeks. However, accurate correlation coefficient was reported with NDVI in all treatments, whereas chlorophyll did not show a direct relation. Conclusion The result of the study confirmed the useful GreanSeeker as an accurate and fast technology for prediction of NDVI. Among different fertilizer treatments of cucumber, 3rd one showed the acceptable results. Since tomatoes did not reach to fertility stage, it would not possible to extract the best nitrogen fertilizer treatments. It is obvious that evaluation of pots in complete growth stages reach us to codify manual fertilization.
