To model the effect of two tillage operations (i.e. conventional and minimum tillage) and seven soil amendments (i.e. C, F, RF, RFM, RTiP, RML, RTiM) on the responses of Zea Mays L. (i.e. corn and stover yields, plant height at 6th and 10th leaf phases, and relative chlorophyll content of the crop leaves at 6th and 10th leaf phases), two-class and four-class classification modeling using the machine learning and multi-layer perceptron principles was performed. To examine the effect of different algorithms considered in the models (i.e. Decision Tree Classifier, Support Vector Machine (SVM) Classifier, K-Nearest Neighbors (KNN) Classifier, and Naive Bayes Classifier as standard Machine Learning (ML) algorithms, and Multi-Layer Perceptron (MLP) Classifier as a Deep Learning (DL) algorithm) on the model performance, classification accuracy and confusion matrix, as well as precision, recall and F1 score indicators were used as the model evaluation metrics. According to the results of this study, among the standard ML algorithms considered herein, application of the SVM classifying algorithm led to relatively higher modeling accuracies; therefore, the SVM algorithm was selected as the most appropriate ML algorithm in this research. Furthermore, when the SVM algorithm was used to classify different corn yield values and the number of classes increased from 2 to 4, the accuracy of the model reduced from 0.97 to 0.82; therefore, there is a trade-off between the number of classes and the accuracy of the model. Moreover, similarity between the result of the model developed herein regarding the effect of tillage type and soil amendments on corn yield classes and the ANOVA result of the other study conducted on similar dataset, acted as cross checking for the appropriateness of the model developed in this study. Finally, application of the MLP algorithm to classify each of the dependent variables considered herein, resulted in higher accuracies compared to the accuracies of the other standard ML algorithms. تفاصيل المقالة

Background and objective: Spatiotemporal maps are suitable tools to convey information to the interested audience. The aim of this paper is to create continent-wide spatiotemporal maps regarding the role of agriculture on CO2-eq production in the period between 1990 and 2019 using the t-map package of R software.Materials and methods:Initial data were obtained from the Internet resources (the FAO, and ARCGIS websites), and after performing some adjustments and modifications i.e. deletion of unnecessary data and matching of the contents of the FAO and ARCGIS data files, as well as combining data files, final data were uploaded to the R software to convert to spatiotemporal maps using the t-map package. Results and conclusion: The results showed a decreasing trend of the share of agriculture in total CO2-eq production from 1990 to 2019. Atthe same time, the amount of agriculture-induced CO2-eq has increased very gradually. On the other hand, the amount of total CO2-eq produced has grown considerably from 1990 to 2019; therefore, it can be concluded that the growth of CO2-eq production in the other economic sectors is higher than that of agriculture. Thus, the first priority should be to curb the growth of CO2-eq production in all economic sectors, especially non-agricultural ones. تفاصيل المقالة

Comparison of Iran Provinces Regarding to the Chemical Fertilizer Consumption in Crop Production Using the t-map Package of the R Software Iman Ahmadi Department of Agronomy, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran Corresponding author E-mail: i_ahmadi_m@yahoo.com Received: 8 March 2019 Accepted: 10 Janu 2020 Abstract One of the best method for presenting both spatial and temporal information in a map is through spatiotemporal maps. In this study, creation of spatiotemporal maps of chemical fertilizer consumption in Iran agriculture has been considered. The necessary primary data of this study,that contained recorded data of the years 1395 to 1399, was obtained from Internet resources and after some modifications with the aid of the t-map package of the R software, final data was converted to spatiotemporal maps. According to the results of this study, the largest chemical fertilizer consumer among Iran provinces was the Khuzestan province that consumed more than 200000 tons per year in the all years considered herein. Other provinces with high fertilizer consumption have been Fars, Golestan, Khorasan-e-Razavi, Mazandartan, and Kermanshahan. Moreover, provinces located in the Iran's central Kavir consumed more chemical fertilizer per unit area of croplands. For example, specific fertilizer consumption of Yazd province is more than kg ha-1 in this time period. It seems that the farmers of these provinces have tried to compensate for the severe environmental conditions for crop production in these regions by aiding the crops with more chemical fertilizing. Keywords: Chemical fertilizer, R software, Spatiotemporal map تفاصيل المقالة

Iman Ahmadi1* Department of genetics and plant production engineering, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran ⃰ Corresponding author Email: i_ahmadi_m@yahoo.com Received: 26 October 2020 Accepted: 25 January 2021 Abstract Many random variables experience both spatial and temporal variability. In scientific terminology these variables have been called spatiotemporal variables. For example most of the data on agriculture, geography, medicine, etc have a spatiotemporal nature. To have a suitable understanding of these variables, it is a good idea to present them on a map having an animated format. One of the best platforms that can perform this duty is R. The reasons of popularity of R is as follows: R is an open-source, platform-independent, still growing software. It has lots of packages and is great for statistical analysis. R is well suited for Machine Learning, and lets you perform data wrangling. The R contains a package named t-map that can be used to create spatiotemporal maps. In this report, the creation of a spatiotemporal map of pesticide consumption per unit area for crop production in different continents between 1990 and 2020 with the aid of the open source R software has been summarized. The aim of this report to introduce this software Therefore, it focuses only on the methodology of map creation with the final goal of motivating agriculturalists to use this software in presenting their future studies. تفاصيل المقالة