Estimation of croplands using indicator kriging and fuzzy classification

Silva, Alessandra Fagioli da; Barbosa, Ana Paula; Zimback, Célia Regina Lopes; Landim, Paulo Milton Barbosa; Soares, Amílcar

doi:10.1016/j.compag.2014.11.020

Cited by 24 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is a simple derived statistic that measures the proportion of all possible cases of presence or absence that are predicted correctly by a model after accounting for chance predictions. Similar to the overall accuracy, a higher kappa index indicates a high model performance [68,69] (Equation 3):…”

Section: Models Evaluationmentioning

confidence: 99%

“…Comparable to the land suitability classes of rain-fed wheat, the kappa index and overall accuracy for predicting land suitability classes of barley were higher for RF (0.69 and 0.73, respectively) than for SVM (0.58 and 0.66, respectively). Based on classes of kappa index values defined by [68,69], the RF, and SVM ML models for predicting land suitability class of rain-fed wheat and barley have a strong and moderate ability to predict land suitability classes, respectively. From a statistical point of view, the RF model performed well in terms of prediction ability.…”

Section: Comparison Of Different ML Modelsmentioning

confidence: 99%

“…The ML-based land suitability maps for rain-fed wheat and barley had higher kappa index values and overall accuracy (0.77 and 0.79; 0.69 and 0.73, respectively) compared to traditional land suitability maps (0.45 and 0.50; 0.43 and 0.47, respectively). Based on the class limits of the kappa index established by [68,69], ML-based land suitability maps of rain-fed wheat and barley have strong levels of accuracy and traditional land suitability maps of rain-fed wheat and barley have moderate levels of accuracy. ML-based and traditional approaches are similar in that they both make use of relationships between soil properties and more readily observable land surface properties.…”

Section: Comparing Traditional and Ml-based Approachesmentioning

confidence: 99%

See 2 more Smart Citations

Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models

et al. 2020

View full text Add to dashboard Cite

Land suitability assessment is essential for increasing production and planning a sustainable agricultural system, but such information is commonly scarce in the semi-arid regions of Iran. Therefore, our aim is to assess land suitability for two main crops (i.e., rain-fed wheat and barley) based on the Food and Agriculture Organization (FAO) “land suitability assessment framework” for 65 km2 of agricultural land in Kurdistan province, Iran. Soil samples were collected from genetic layers of 100 soil profiles and the physical-chemical properties of the soil samples were analyzed. Topography and climate data were also recorded. After calculating the land suitability classes for the two crops, they were mapped using machine learning (ML) and traditional approaches. The maps predicted by the two approaches revealed notable differences. For example, in the case of rain-fed wheat, results showed the higher accuracy of ML-based land suitability maps compared to the maps obtained by traditional approach. Furthermore, the findings indicated that the areas with classes of N2 (≈18%↑) and S3 (≈28%↑) were higher and area with the class N1 (≈24%↓) was less predicted in the traditional approach compared to the ML-based approach. The major limitations of the study area were rainfall at the flowering stage, severe slopes, shallow soil depth, high pH, and large gravel content. Therefore, to increase production and create a sustainable agricultural system, land improvement operations are suggested.

show abstract

Section: Models Evaluationmentioning

confidence: 99%

Section: Comparison Of Different ML Modelsmentioning

confidence: 99%

Section: Comparing Traditional and Ml-based Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models

et al. 2020

View full text Add to dashboard Cite

show abstract

“…It was developed to determine the degree of coherence between two scores at the classification level (Cohen, 1960).The Kappa statistic takes values from -1 to 1. The following limits of agreement were used: (1) None: <0, (2) Poor: 0-0.19, (3) Weak: 0.20-0.39, (4) moderate: 0.40-0.59, (5) Strong: 0.60-0.79, (6) Excellent: 0.80-1 (Da Silva et al, 2015;INPE, 2001). Correlation and regression calculations were made between indices.…”

Section: Methodsmentioning

confidence: 99%

Determination of Agricultural Land Suitability Classes for Samsun Province Based on Parametric and Hierarchy Approaches

Turan

Dengi̇z

2019

Lnternational Journal of Geography and Geography Education

View full text Add to dashboard Cite

Orhan DENGİZ 2 ÖzArazi kalite indeksi agro-ekosistemlerinin değerlendirilmesinde önemli bir araçtır. Bu çalışmanın amacı, parametrik (AKIg) ve hiyerarşik (AKIa) yaklaşımlı iki farklı arazi kalite indeks modeli kullanılarak Samsun iline ait arazilerin tarımsal amaçlı arazi uygunluk sınıflamasının belirlenmesi ve haritalanmasıdır. 9579 km 2 alana sahip olan Samsun ilinden 995 adet yüzey toprak örneklemesi yapılmıştır. Arazi özelliklerinden derinlik ve eğim, fizikokimyasal toprak özelliklerinden ise bünye, pH, EC, kireç, verimlilik özelliklerinden ise fosfor, potasyum ve azot olmak üzere toplam 9 faktör ile toplam veri seti (TVS) oluşturulmuştur. Minimum veri setin (MVS) oluşturulmasında ise temel bileşenler analizi uygulanmıştır. TVS'ne göre AKIa ve AKIg modellerine ait dağılım haritalarının oluşturulmasında Kriging'in basit üssel ve Gaussian modelleri kullanılmıştır. Her iki modele göre çalışma alanının yaklaşık %15'i işlemeli tarıma arazi kalitesi bakımından hiçbir zaman uygun değilken, yaklaşık % 30'u ise çok uygun ve uygun olduğu belirlenmiştir. MVS'ne göre AKIa ve AKIg modellerine ait dağılım haritalarının oluşturulmasında ise Kriging'in basit üssel ve doğal küresel modelleri kullanılmıştır. Buna göre, AKİa için toplam alanın %29,5'si çok uygun ve uygun iken, AKİg yaklaşımı için % 22.1'i uygun ve çok uygun sınıf olarak belirlenmiştir. Ayrıca, TVS ve MVS'ne göre AKIa ve AKIg lineer korelasyon ve kappa istatistik analizleri ile karşılaştırıldığında ise TVS-AKIa modelinin en yüksek değere sahip olduğu belirlenmiştir. AbstractLand quality index is an important tool for evaluating agro-ecosystem. The aim of this study is to determine and agricultural land suitability classes for Samsun province based on two different land quality indexes model (parametric-AKIg and hierarchy-AKIa) approaches and to create maps of them. Total 995 soil samples were taken from soil surface (0-20cm) in Samsun province covers about 9579 km 2 . Total data set (TDS) consists of nine land and physic-chemical soil properties (soil depth, slope, texture, pH, EC, lime content, nitrogen, phosphorus, and potassium. In order to generate MDS, principal component analysis was done. Exponential and Gaussian of simple kriging models were used to generate distribution map of the AKIa and AKIg suitability classes in TDS. According to results, about 15% total study area is not suitable for agricultural activities whereas, about 30% of it is suitable and highly suitable for agricultural usage. In addition, Exponential simple of kriging models were used to generate distribution map of the AKIa and AKIg suitability classes in MDS. According to results, about 29.5% total study area was found as suitableand highly suitable for agricultural activities in AKIa model while, about 22.1% of it is suitable and highly suitable for agricultural usages in AKIg model. Moreover, the results of linear correlation and kappa statistical analysis showed that land quality was better estimated using AKIa, compared to the AKIg in TDS and MDS.

show abstract

“…Geostatistical methods find wide applications, for example in geology, meteorology, hydrology and ecology, such as kriging, have been introduced into soil science to provide estimation at unsampled locations [18]- [21]. With the application of geostatistical methods, Huang et al [22] mapped spatial patterns of soil salinity on the field scale from aboveground electromagnetic induction (EM) readings by substantially reducing the number of soil samples.…”

Section: Introductionmentioning

confidence: 99%

Quantitative Evaluation and Uncertainty Assessment on Geostatistical Simulation of Soil Salinity Using Electromagnetic Induction Technique

Wang¹,

Ren²,

Hao³

et al. 2016

JEP

View full text Add to dashboard Cite

Diagnosis of soil salinity and characterizing its spatial variability both vertically and horizontally are needed to establish control measures in irrigated agriculture. In this regard, it is essential that salinity development in varying soil depths be known temporally and spatially. Apparent soil electrical conductivity, measured by electromagnetic induction instruments, has been widely used as an auxiliary variable to estimate spatial distribution of field soil salinity. The main objectives of this paper were adopted a mobile electromagnetic induction (EMI) system to perform field electromagnetic (EM) survey in different soil layers, to evaluate the uncertainty through Inverse Distance Weighted (IDW) and Ordinary Kriging (OK) methods, and to determine which algorithm is more reliable for the local and spatial uncertainty assessment. Results showed that EM38 data from apparent soil electrical conductivity are highly correlated with salinity, more accurate for estimating salinity from multiple linear regression models, which the correlation coefficient of 0-20, 20-40, 40-60 and 60-80 cm were 0.9090, 0.9228, 0.896 and 0.9085 respectively. The comparison showed that the prediction accuracy of two methods also displays good performance for soil salinity, the estimation precision of IDW method (with E = 0.8873, 0.9075, 0.8483 and 0.901, RPD = 9.64, 8.01, 8.17 and 11.23 in 0-20, 20-40. 40-60 and 60-80 cm soil layers, respectively) was superior to that of OK (with E = 0.8857, 0.872, 0.8744 and 0.8822, RPD = 9.44, 7.83, 8.52 and 10.88, respectively), but differences of two methods in predictions are not significant. The obtained salinity map was helpful to display the spatial patterns of soil salinity and monitor and evaluate the management of salinity.

show abstract

Estimation of croplands using indicator kriging and fuzzy classification

Cited by 24 publications

References 42 publications

Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models

Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models

Determination of Agricultural Land Suitability Classes for Samsun Province Based on Parametric and Hierarchy Approaches

Quantitative Evaluation and Uncertainty Assessment on Geostatistical Simulation of Soil Salinity Using Electromagnetic Induction Technique

Contact Info

Product

Resources

About