A deep learning image segmentation model for agricultural irrigation system classification

Raei, Ehsan; Asanjan, Ata Akbari; Nikoo, Mohammad Reza; Sadegh, Mojtaba; Pourshahabi, Shokoufeh; Adamowski, Jan

doi:10.1016/j.compag.2022.106977

Cited by 23 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Irrigation systems modulate agricultural productivity, and are associated with significant implications for the soil, water resources, sustainable development and the environment. Efficient irrigation systems lead to a substantial decrease in labor and water needs in comparison with traditional surface irrigation methods (Raei et al, 2022). In the territory of Zhambyl region, all the diversity of soil is distributed by zones -high-mountain, mountain-steppe, lowmountain and foothill, desert.…”

Section: Resultsmentioning

confidence: 99%

“…Based on the statistical data of the Land Resources Committee of Zhambyl region of the Republic of Kazakhstan and preliminary regional plan, using remote sensing data, a map of the land fund of Zhambyl region was created (Figure 1), which allowed us to assess its structure and territorial distribution of the region's land by categories. The majority of issues associated with the territorial distribution of the land fund of the Zhambyl region require methods that can be integrated in GIS, which are powerful tools designed for managing, transforming and representing referenced data spatially (Dehimi, 2021) Mapping farmlands with different land use categories is important for understanding regional water needs, agricultural production, water resources consumption and vulnerability to climatic extremes (Raei et al, 2022).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Assessment of Land Resources of the Zhambyl Region as the Basis of Recreation Development and Food Security of the Republic of Kazakhstan

ALDAZHANOVA¹,

Beissenova²,

SKORINTSEVA³

et al. 2022

GTG

View full text Add to dashboard Cite

The article presents the scientific results of a study for the assessment of agricultural land in Zhambyl region of the Republic of Kazakhstan based on field studies in 2020-2021 and modern GIS technologies. The purpose of the study of the article is a comprehensive assessment of land resources used for agricultural production in Zhambyl region, identifying the prevailing areas of agricultural land, irrigated and rainfed pastures by administrative districts of the region. In the course of the scientific study, proven Kazakhstani methods of assessing the state of agricultural land, successfully applied to the arid agricultural regions of Kazakhstan, as well as methods of geographical and agricultural sciences for land analysis and calculation according to the structure of use, were used. Based on the statistical data of the Committee of Land Resources and preliminary regional plans, a map of the land fund of the Zhambyl region by land categories was created. The results of the study allow business entities, especially farms, to organize the rational use of irrigated lands, including pastures and hayfields, including the sustainability and profitability of agricultural production, as well as successfully develop agro-landscape tourism.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Assessment of Land Resources of the Zhambyl Region as the Basis of Recreation Development and Food Security of the Republic of Kazakhstan

ALDAZHANOVA¹,

Beissenova²,

SKORINTSEVA³

et al. 2022

GTG

View full text Add to dashboard Cite

show abstract

“…For semantic segmentation algorithms, image labeling is a necessary step for training a supervised model [37,38]. In this step, all diagnostic horizons are manually delineated using the Labelme software package [39] based on existing soil profile descriptions.…”

Section: Image Labelingmentioning

confidence: 99%

Toward Field Soil Surveys: Identifying and Delineating Soil Diagnostic Horizons Based on Deep Learning and RGB Image

2022

View full text Add to dashboard Cite

The diagnostic horizon in a soil is reflective of the environment in which it developed and the inherent characteristics of the material, therefore quantitative approaches to horizon delineation should focus on the diagnostic horizon. Moreover, it can enable the exchange and transfer of soil information between different taxonomic systems. This study aims to explore the use of deep learning and RGB images to train a soil diagnostic horizon identification model that can help field workers determine soil horizon information quickly, efficiently, easily, and cost-effectively. A total of 331 soil profile images of the main soil categories (five soil orders, including Primosols, Ferrosols, Argosols, Anthrosols, and Cambosols) from Hubei and Jiangxi Provinces were used. Each soil profile image was preprocessed and augmented to 10 images and then inputted into the UNet++ architecture. The mean intersection over union and pixel accuracy of the model were 71.24% and 82.66%, respectively. Results show that the model could accurately identify and delineate the soil diagnostic horizons. Moreover, the model performance varied considerably due to the definition of the horizon and whether the diagnostic conditions applied to a wide range of visual features on RGB images, the number of samples, and the soil characteristics of the study area.

show abstract

“…The paper also provides fresh insights into the effects of transfer learning, imbalanced training data, and the effectiveness of different model topologies for multiple irrigation type segmentation. Applying very high-resolution remote sensing images, such as those from commercial satellites, the suggested deep segmentation model can categories a variety of irrigation systems at regional to global sizes [72]. Convex hull center priori and Markov adsorption chain-based is used for apple picture segmentation.…”

Section: Agriculture and Biological Sciencementioning

confidence: 99%

Image Segmentation Using Hybrid Optimization Algorithms: Review

Hemeida¹,

Yahya

Al-Sanary

2022

Aswan University Journal of Sciences and Technology

View full text Add to dashboard Cite

Image segmentation, often based on the properties of image pixels, is a widely used method in digital image processing and analysis to divide an image into multiple parts or areas. The main goal of image segmentation is to simplify the image for easier analysis. It would be very difficult to implement computer vision without performing image segmentation. An important component of computer vision is image segmentation, which has numerous commercial applications. Google and others Image-based search engines use image segmentation algorithms to identify the objects in your image and match their results to the relevant images they find to present you with search results.

show abstract

A deep learning image segmentation model for agricultural irrigation system classification

Cited by 23 publications

References 43 publications

Assessment of Land Resources of the Zhambyl Region as the Basis of Recreation Development and Food Security of the Republic of Kazakhstan

Assessment of Land Resources of the Zhambyl Region as the Basis of Recreation Development and Food Security of the Republic of Kazakhstan

Toward Field Soil Surveys: Identifying and Delineating Soil Diagnostic Horizons Based on Deep Learning and RGB Image

Image Segmentation Using Hybrid Optimization Algorithms: Review

Contact Info

Product

Resources

About