Pesticide consumption and environmental pollution in orchards can be greatly decreased by combining variable-rate spray treatments with proportional control systems. Nowadays, farmers can use variable-rate canopy spraying to apply weed killers only where they are required which provides environmental friendly and cost-effective crop protection chemicals. Moreover, restricting the use of pesticides as Plant Protection Products (PPP) while maintaining appropriate canopy deposition is a serious challenge. Additionally, automatic sprayers that adjust their application rates to the size and shape of orchard plantations has indicated a significant potential for reducing the use of pesticides. For the automatic spraying, the existing research used an Artificial Intelligence and Machine Learning. Also, spraying efficiency can be increased by lowering spray losses from ground deposition and off-target drift. Therefore, this study involves a thorough examination of the existing variable-rate spraying techniques in orchards. In addition to providing examples of their predictions and briefly addressing the influences on spraying parameters, it also presents various alternatives to avoiding pesticide overuse and explores their advantages and disadvantages.
The article solves the problem of verifying oil spills on the water surfaces of rivers, seas and oceans using optical aerial photographs, which are obtained from cameras of unmanned aerial vehicles, based on deep learning methods. The specificity of this problem is the presence of areas visually similar to oil spills on water surfaces caused by blooms of specific algae, substances that do not cause environmental damage (for example, palm oil), or glare when shooting (so-called look-alikes). Many studies in this area are based on the analysis of synthetic aperture radars (SAR) images, which do not provide accurate classification and segmentation. Follow-up verification contributes to reducing environmental and property damage, and oil spill size monitoring is used to make further response decisions. A new approach to the verification of optical images as a binary classification problem based on the Siamese network is proposed, when a fragment of the original image is repeatedly compared with representative examples from the class of marine oil slicks. The Siamese network is based on the lightweight VGG16 network. When the threshold value of the output function is exceeded, a decision is made about the presence of an oil spill. To train the networks, we collected and labeled our own dataset from open Internet resources. A significant problem is an imbalance of classes in the dataset, which required the use of augmentation methods based not only on geometric and color manipulations, but also on the application of a Generative Adversarial Network (GAN). Experiments have shown that the classification accuracy of oil spills and look-alikes on the test set reaches values of 0.91 and 0.834, respectively. Further, an additional problem of accurate semantic segmentation of an oil spill is solved using convolutional neural networks (CNN) of the encoder-decoder type. Three deep network architectures U-Net, SegNet, and Poly-YOLOv3 have been explored for segmentation. The Poly-YOLOv3 network demonstrated the best results, reaching an accuracy of 0.97 and an average image processing time of 385 s with the Google Colab web service. A database was also designed to store both original and verified images with problem areas.
One of the most important tasks in practical agricultural activity is the identification of agricultural crops, both those growing in individual fields at the moment and those that grew in these fields earlier. To reduce the complexity of the identification process in recent years, data from remote sensing of the Earth (remote sensing), including the values of vegetation indices calculated during the growing season, have been used. At the same time, processing optical satellite images and obtaining reliable index values is often difficult, which is due to cloud cover during the shooting. To solve this problem, the article suggests using the seasonal course curve of the radar vegetation index with double polarization (DpRVI) as the main indicator characterizing agricultural crops. In the period 2017-2020, 48 radar images of the Khabarovsk Municipal District of the Khabarovsk Territory from the Sentinel-1 satellite were received and processed to identify crops in the experimental fields of the Far Eastern Research Institute of Agriculture (FEARI) (resolution 22 m, shooting interval - 12 days). Soybeans and oats were the main identified crops. Pixels of fields not occupied by these crops (forage grasses, abandoned fields) were also added. The series of values of DpRVI were obtained both for individual pixels and fields, and approximated series for three classes. The approximation was carried out using the Gaussian function, the double logistic function, the square and cubic polynomials. It is established that the optimal approximation algorithm is the use of a double logistic function (the average error was 4.6%). On average, the approximation error of the vegetation index for soybeans did not exceed 5%, for perennial grasses – 8.5%, and for oats - 11%. For experimental fields with a total area of 303 hectares with a known crop rotation, the classification was carried out by the weighted method of k nearest neighbors (the training sample was formed according to the data of 2017-2019, the test sample -2020). As a result, 90% of the fields were correctly identified, and the overall pixel classification accuracy was 73%, which made it possible to identify the discrepancy between the actual boundaries of the fields declared to identify abandoned and swampy areas. Thus, it is established that the DpRVI index can be used to identify agricultural crops in the south of the Far East and serve as the basis for the automatic classification of arable land.
This article is devoted to evaluation of the effectiveness of the spacecraft remote sensing of the Earth. The probability of monitoring the spacecraft remote sensing of the specified area is proposed as a generalized indicator of the effectiveness. That probability depends on the probability of the reception of information about the object and the probability of occurrence of data transmission to the point of processing through the channels of satellite communication systems. The probability of obtaining information about an object is determined by the probability of object detection in the area and probability of its identification. The focus is on the estimation of the probability of object detection in a service area. This figure has a geometric meaning, which determines the percentage of the area surface viewed by the spacecraft. The calculation of geometric probability is generally performed using R-functions. The work includes mathematical description of the span and area of service by the final mathematical expressions, on the basis of which correlations to calculate area-based indicators of the viewing areas of the earth's surface were obtained.
In this paper the ability to use neurocomputer technology to imaging remote sensing system are considered. The modeling of object classification is reviewed. The sequence and contents of the main stages of the construction of the neural network architecture are discussed. The spectral characteristics of different ground objects are used for classification and recognition of objects in satellite images. Comparative analysis of different types of neural networks in the classification of ground objects is given.
A brief analysis of the state of preparation of the specialists in the field of spaceground monitoring, summarized the experience of the training, proposals and recommendations to improve and intensify the efforts of interested institutions and organizations in the preparation of the specialists of the desired level and profile.
Basic stages of high and super-high resolution space borne synthetic aperture radar data interferometric processing are reviewed. The results of experimental research of the digital elevation maps accuracy with processing by different phase noise filtration algorithms and phase unwrapping methods are presented.
1 - 7 of 7 items