comparison of artificial neural network and decision tree methods for mapping soil units in ardakan region

Authors

روح اله تقی زاده مهرجردی

استادیار، دانشکدة کشاورزی و منابع طبیعی دانشگاه اردکان فریدون سرمدیان

استاد، دانشکدة مهندسی و فناوری کشاورزی، پردیس کشاورزی و منابع طبیعی دانشگاه تهران محمود امید

استاد، دانشکدة مهندسی و فناوری کشاورزی، پردیس کشاورزی و منابع طبیعی دانشگاه تهران غلامرضا ثواقبی

استاد، دانشکدة مهندسی و فناوری کشاورزی، پردیس کشاورزی و منابع طبیعی دانشگاه تهران نورایر تومانیان

abstract

in response to the demand for soil spatial information, the acquisition of digital auxiliary data and their matching with field soil observations is on the increase. with the harmonization of these data sets, through computer based methods, the so-called digital soil maps are increasingly being found to be as reliable as the traditional soil mapping practices, and with no prohibitive costs. therefore, in the present research, it has been attempted to develop decision tree (dta) and artificial neural network (ann) models for spatial prediction of soil taxonomic classes in an area covering about 720 km2 located in an arid region of central iran where traditional soil survey methods are very difficult to undertake. within this using the conditioned latin hypercube sampling method, location of 187 soil profiles were spotted and then described, sampled, analyzed and allocated in taxonomic classes according to soil taxonomy of america. auxiliary data used in this study to represent predictive soil forming factors were terrain attributes, landsat 7 etm+ data and a geomorphologic surfaces map. results revealed that dta benefited from a the higher accuracy than ann for about 7% as regarded the prediction of soil classes. a determination of coefficient (r2), overall accuracy and, kappa coefficient calculated for the two models were recorded as 0.34, 0.46, 48%, 52%, and 0.13 vs. 0.25, respectively. the results revealed some auxiliary variables as having more influence on the predictive soil class model. wetness index, geomorphology map and multi-resolution index of valley bottom flatness could be named as some of these variables. in general, results showed that decision tree models benefited from a higher accuracy than ann ones, with results as more convenient for interpretation. therefore, use of decision tree models for spatial prediction of soil properties (category and continuous soil data) is recommended in the future studies.

Upgrade to premium to download articles

Sign up to access the full text

Already have an account?login

similar resources

Comparison of artificial neural network and multivariate regression methods in prediction of soil cation exchange capacity (Case study: Ziaran region)

Investigation of soil properties like Cation Exchange Capacity (CEC) plays important roles in study of environmental reaserches as the spatial and temporal variability of this property have been led to development of indirect methods in estimation of this soil characteristic. Pedotransfer functions (PTFs) provide an alternative by estimating soil parameters from more readily available soil data...

full text

Comparison of gestational diabetes prediction with artificial neural network and decision tree models

Background: Gestational diabetes mellitus (GDM) is one of the most common metabolic disorders in pregnancy, which is associated with serious complications. In the event of early diagnosis of this disease, some of the maternal and fetal complications can be prevented. The aim of this study was to early predict gestational diabetes mellitus by two statistical models including artificial neural ne...

full text

Comparison of Artificial Neural Network, Decision Tree and Bayesian Network Models in Regional Flood Frequency Analysis using L-moments and Maximum Likelihood Methods in Karkheh and Karun Watersheds

Proper flood discharge forecasting is significant for the design of hydraulic structures, reducing the risk of failure, and minimizing downstream environmental damage. The objective of this study was to investigate the application of machine learning methods in Regional Flood Frequency Analysis (RFFA). To achieve this goal, 18 physiographic, climatic, lithological, and land use parameters were ...

full text

digital mapping of soil texture using regression tree and artificial neural network in bijar, kurdistan

soil texture is an important soil physical property that governs most physical, chemical, biological, and hydrological processes in soils. detailed information on soil texture variability is crucial for proper crop and land management and environmental studies. therefore, at present research, 103 soil profiles were dogged and then sampled in order to prepare digital map of soil texture in bijar...

full text

Comparison of disability score estimation in multiple sclerosis patients with artificial neural network and decision tree models

Background: Multiple Sclerosis (MS) is one of the most debilitating disease among young adults. Understanding the disability score (Expanded Disability Status Scale (EDSS)) of these patients is helpful in choosing their treatment process. Calculating EDSS takes a lot of time for Neurologists, so having a way to estimate EDSS can be helpful. This study aimed to estimate the EDSS score of MS pati...

full text

Early Prediction of Gestational Diabetes Using ‎Decision Tree and Artificial Neural Network Algorithms

Introduction: Gestational diabetes is associated with many short-term and long-term complications in mothers and newborns; hence, the detection of its risk factors can contribute to the timely diagnosis and prevention of relevant complications. The present study aimed to design and compare Gestational diabetes mellitus (GDM) prediction models using artificial intelligence algorithms. Materials ...

full text

My Resources

Save resource for easier access later


Journal title:
تحقیقات آب و خاک ایران

جلد ۴۴، شماره ۲، صفحات ۱۷۳-۱۸۲

Keywords
in response to the demand for soil spatial information the acquisition of digital auxiliary data and their matching with field soil observations is on the increase. with the harmonization of these data sets through computer based methods the so called digital soil maps are increasingly being found to be as reliable as the traditional soil mapping practices and with no prohibitive costs. therefore in the present research it has been attempted to develop decision tree (dta) and artificial neural network (ann) models for spatial prediction of soil taxonomic classes in an area covering about 720 km2 located in an arid region of central iran where traditional soil survey methods are very difficult to undertake. within this using the conditioned latin hypercube sampling method location of 187 soil profiles were spotted and then described sampled analyzed and allocated in taxonomic classes according to soil taxonomy of america. auxiliary data used in this study to represent predictive soil forming factors were terrain attributes landsat 7 etm+ data and a geomorphologic surfaces map. results revealed that dta benefited from a the higher accuracy than ann for about 7% as regarded the prediction of soil classes. a determination of coefficient (r2) overall accuracy and kappa coefficient calculated for the two models were recorded as 0.34 0.46 48% 52% and 0.13 vs. 0.25 respectively. the results revealed some auxiliary variables as having more influence on the predictive soil class model. wetness index geomorphology map and multi resolution index of valley bottom flatness could be named as some of these variables. in general results showed that decision tree models benefited from a higher accuracy than ann ones with results as more convenient for interpretation. therefore use of decision tree models for spatial prediction of soil properties (category and continuous soil data) is recommended in the future studies.

Hosted on Doprax cloud platform doprax.com

copyright © 2015-2023