Soil provides a key interface between the atmosphere and the lithosphere and plays an important role in food production, ecosystem services, and biodiversity. Recently, demands for applying machine learning (ML) methods to improve the knowledge and understanding of soil behavior have increased. While real-world datasets are inherently imbalanced, ML models overestimate the majority classes and underestimate the minority ones. The aim of this study was to investigate the effects of imbalance in training data on the performance of a random forest model (RF). The original dataset (imbalanced) included 6100 soil texture data from the surface layer of agricultural fields in northern Iran. A synthetic resampling approach using the synthetic minority oversampling technique (SMOTE) was employed to make a balanced dataset from the original data. Bioclimatic and remotely sensed data, distance, and terrain attributes were used as environmental covariates to model and map soil textural classes. Results showed that based on mean minimal depth (MMD), when imbalanced data was used, distance and annual mean precipitation were important, but when balanced data were employed, terrain attributes and remotely sensed data played a key role in predicting soil texture. Balanced data also improved the accuracies from 44% to 59% and 0.30 to 0.52 with regard to the overall accuracy and kappa values, respectively. Similar increasing trends were observed for the recall and F-scores. It is concluded that, in modeling soil texture classes using RF models through a digital soil mapping approach, data should be balanced before modeling.

Climate plays a key role in ecosystem services. Understanding microclimate change can be a significant help in making the right decision for ecosystems and buffering the effects of global warming. Given the large distances between meteorological stations and the changes in the climate variables within short distances, such variations cannot be detected just by using observed meteorological data. This study aimed at determining the spatial structure of the mean annual temperature, the annual average precipitation, and the climate zoning of Iran using data from 3825 stations from 2002 to 2016.The multivariate regression demonstrated the dependence of these variables on longitude, latitude, and elevation. Regression-kriging indicated a decline in temperature from east to west and northwest in high-altitude areas, while most precipitation values were observed over the Caspian Sea coastline and the Zagros Mountains. Climatic zoning showed that using auxiliary variables was very effective in detecting 24 climatic classes and understating the climate diversity in Iran. Hot to very hot and arid to very arid climate classes occupy the largest part of Iran, including the southeastern and southern desert regions. According to the generated climatic map, the large climatic diversity of Iran needs accurate policymaking regarding cultivation patterns and biodiversity. Visual comparisons of climatic zones with four remotely sensed agricultural-related variables showed that using such carefully produced climatic maps would be beneficial in classifying, assessing, and interpreting the remote sensed agricultural-related variables.

Recently, the demand for high-quality land use/land cover (LULC) information for near-real-time crop type mapping, in particular for multi-relief landscapes, has increased. While the LULC classes are inherently imbalanced, the statistics generally overestimate the majority classes and underestimate the minority ones. Therefore, the aim of this study was to assess the classes of the 10 m European Satellite Agency (ESA) WorldCover 2020 land use/land cover product with the support of the Google Earth Engine (GEE) in the Honam sub-basin, south-west Iran, using the LACOVAL (validation tool for regional-scale land cover and land cover change) online platform. The effect of imbalanced ground truth has also been explored. Four sampling schemes were employed on a total of 720 collected ground truth points over approximately 14,100 ha. The grassland and cropland totally canopied 94% of the study area, while barren land, shrubland, trees and built-up covered the rest. The results of the validation accuracy showed that the equalized sampling scheme was more realistically successful than the others in terms of roughly the same overall accuracy (91.6%), mean user’s accuracy (91.6%), mean producers’ accuracy (91.9%), mean partial portmanteau (91.9%) and kappa (0.9). The product was statistically improved to 93.5% ± 0.04 by the assembling approach and segmented with the help of supplementary datasets and visual interpretation. The findings confirmed that, in mapping LULC, data of classes should be balanced before accuracy assessment. It is concluded that the product is a reliable dataset for environmental modeling at the regional scale but needs some modifications for barren land and grassland classes in mountainous semi-arid regions of the globe.

The demand for high quality and low-cost spatial distribution information of soil texture classes (STCs) is of great necessity in developing countries. This paper explored digital mapping of topsoil STCs using soil fractions, terrain attributes and artificial neural network (ANN) algorithms. The 4493 soil samples covering 10 out of 12 STCs were collected from the rice fields of the Guilan Province of Northern Iran. Nearly 75% of the dataset was used to train the ANN algorithm and the remaining 25% to apply a repeated 10-fold cross-validation. Spatial prediction of soil texture fractions was carried out via geostatistics and then a pixel-based approach with an ANN algorithm was performed to predict STCs. The ANN presented reasonable accuracy in estimating USDA STCs with a kappa coefficient of 0.38 and pixel classification accuracy percentage of 52%. Hybridizing soil particles with relief covariates yielded better estimates for coarse- and medium-STCs. The results also showed that clay particle and terrain attributes are more important covariates than plant indices in areas under single crop cultivation. However, it is recommended to examine the approach in areas with diverse vegetation cover.

Improving agricultural sustainability and increasing production are the most important goals for the near future especially for developing countries. Accordingly, in these countries, a land suitability evaluation (LSE) study based on the FAO framework is recommended, whereas the high cost caused a dramatic reduction in LSE studies particularly in irrigated paddy fields. Therefore, in this study two depth scenarios (scenario2: 0–50cm and scenario3: 0–25cm) were compared to the FAO framework depth scenario (scenario1: 0–100cm) to investigate the ability of the two new scenarios in qualitative and quantitative LSE classification for irrigated paddy fields. The study was conducted in Guilan province, Iran. Seventy-seven soil profiles were described, soil samples from genetic layers and 30 yield samples were collected. The results showed that, in both qualitative and quantitative LSE, the calculated values for both new scenarios were significantly correlated to the values in scenario1. Moreover, the coefficient of determination, the paired t-test, and the kappa coefficient showed very strong agreements between the two proposed scenarios and senario1. Overlaying three scenarios maps also didn’t reveal notable differences. Although the use of scenario1 is preferred, scenario2 due to very close results to scenario1 and being time-and-cost-saving, will be recommended.