Digitization of soil organic carbon with artificial neural network and multivariate linear regression in Kurdistan province

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

MAHMOUDZADEH H.; MATINFAR H.R.; TAGHIZADEH MEHRJERDI R.

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: Journal of Soil Management and Sustainable Production Year:2021 | Volume:10 | Issue:4 Page(s): 77-98

Download Full-Text

Persian Verion

View:

561

Download:

Cites:

Information Journal Paper

Title

Digitization of soil organic carbon with artificial neural network and multivariate linear regression in Kurdistan province

Author(s)

MAHMOUDZADEH H. | MATINFAR H.R. | TAGHIZADEH MEHRJERDI R. | Issue Writer Certificate

Keywords

Data MiningQ1

Digital Soil MappingQ2

Soil Organic CarbonQ1

Abstract

Background and Objectives: Organic carbon plays a vital role in climate control and environmental sustainability by retaining a significant portion of its mineralizable organic forms in the soil. Organic carbon also has a key effect on physicochemical and biological properties of soil; in a way, it is called as an indicator of soil health. Therefore, the study of spatial distribution of Soil Organic Carbon to identify areas with carbon sequestration potential is one of the requirements of soil management planning and climate control policy through agricultural activities. Conventional methods for estimating Soil Organic Carbon are costly and time consuming and cannot be replicated and generalized to similar points. In recent years, with the advancement of technology and the growing human need for access to accessible information and cost savings, through Data Mining and with the help of satellite images and auxiliary topographic variables, digitization of soil properties, including Organic carbon is made possible. Digital Soil Mapping is the development of a numerical or statistical model of the relationship between environmental variables and soil properties that is used for large geographic data to produce a digital map. The three main goals of Digital Soil Mapping are: 1) inferring the relationship between environmental variables and soil properties, 2) producing and presenting data that better illustrate soil-geolocation, and 3) explicitly applying expert knowledge in design. They are models. Digital mapping also provides potential advances in soil pedology and geography by providing insights into landfilling processes. Materials and Methods: This study was conducted in Kamyaran city of Kurdistan province in order to predict Soil Organic Carbon. In this study, 110 soil samples were randomly analyzed from different land uses. To better predict the spatial distribution of Soil Organic Carbon in the study area, 101 auxiliary variables extracted from digital elevation model, satellite images and climatic variables have been used. Prediction of Soil Organic Carbon was modeled with two models of multivariate linear regression and artificial neural network in Jump software environment. Results: The results showed that the amount of Soil Organic Carbon in the western and northwestern parts of the study area is the highest, which includes areas with forest and rangeland cover. Auxiliary variables: base level of canal network (40%), band 4 (23%), leaf water content (20%), ground roughness (19%), vertical distance to canal network (18%), slope (18%), Normalized vegetation differentiation index (17%), area level (16%), slope direction (16%), height (16%), band 3 (15%), reflective absorption index (14%), band 1 (14 %), Rain (13%), band 5 (13%), air temperature (12%), vegetation index (11%), topographic wetness index (10%) and vegetation difference index (10%) had the greatest effect On the modeling of Soil Organic Carbon in the artificial neural network model. The results of modeling validation showed that the artificial neural network performed better (R2 = 0. 97) than the multivariate linear regression (R2 = 0. 59) prediction of Soil Organic Carbon in the study area. Conclusion: The results of this study showed that the distribution of organic carbon is more influenced by topographic and climatic factors. In areas where sampling is not possible in the whole area for any reason, it can be used through auxiliary variables such as topographic, climatic and vegetation parameters and with modern Data Mining methods to estimate Soil Organic Carbon.

Cites

No record.

References

No record.

Cite

APA: Copy

MAHMOUDZADEH, H., MATINFAR, H.R., & TAGHIZADEH MEHRJERDI, R.. (2021). Digitization of soil organic carbon with artificial neural network and multivariate linear regression in Kurdistan province. ELECTRONIC JOURNAL OF SOIL MANAGEMENT AND SUSTAINABLE PRODUCTION, 10(4 ), 77-98. SID. https://sid.ir/paper/397003/en

Vancouver: Copy

MAHMOUDZADEH H., MATINFAR H.R., TAGHIZADEH MEHRJERDI R.. Digitization of soil organic carbon with artificial neural network and multivariate linear regression in Kurdistan province. ELECTRONIC JOURNAL OF SOIL MANAGEMENT AND SUSTAINABLE PRODUCTION[Internet]. 2021;10(4 ):77-98. Available from: https://sid.ir/paper/397003/en

IEEE: Copy

H. MAHMOUDZADEH, H.R. MATINFAR, and R. TAGHIZADEH MEHRJERDI, “Digitization of soil organic carbon with artificial neural network and multivariate linear regression in Kurdistan province,” ELECTRONIC JOURNAL OF SOIL MANAGEMENT AND SUSTAINABLE PRODUCTION, vol. 10, no. 4 , pp. 77–98, 2021, [Online]. Available: https://sid.ir/paper/397003/en

Related Journal Papers