machine learning algorithms

Urbanization is a growing concern, and satellite images play a crucial role in assessing urban growth. To begin working with satellite images, it is necessary to take samples and classify the images according to the region's complications. In this study, 4 machine learning algorithms (K-Nearest Neighbor, Support Vector Machine, Random Forest(RandomTrees), and Maximum Likelihood) were used to classify images from three periods of Landsat satellite imagery (Landsat 7, 8, 9) at two 10-year intervals (2003, 2013, and 2023). In four areas of Tehran (2, 5, 21, 22), this has been applied to urban growth. Using a specific classification method for time series of images may not produce accurate results to evaluate the changes in a phenomenon, and much depends on the dispersion of the samples taken from the images. Using the KNN method with a Kappa coefficient of 91%, Landsat image 7 performed best due to the uniformity of the samples. Additionally, Landsat images 8 and 9 were successfully analyzed with the SVM method with an accuracy of 97% and 94%, respectively, as well as a Kappa coefficient of 95% and 89%. Urban growth is also evaluated using selected methods for each image. Between 2003 and 2013, urban growth was 10%, between 2013 and 2023, it was 24%, and as a result, between 2023 and 2003, it was 34%. Additionally, we examine the change in barren and green lands in this study. Our study offers the most accurate hybrid approach to image classification for urban growth, and it can provide valuable information to urban planners and policymakers for managing urban growth and promoting sustainable development in cities.

Plastic concrete is an engineering material, which is commonly used for construction of cut-off walls to prevent water seepage under the dam. This type of concrete shows great promise    to satisfy the requirements of the strength, stiffness and permeability for remedial cut-off wall construction. This paper aims to explore three hybrid machine learning algorithms including Artificial Neural Network (ANN), Support Vector Machine (SVM) and Adaptive Neuro-Fuzzy Inference System (ANFIS) optimized with Particle Swarm Optimization (PSO) to predict the compressive and splitting tensile strength of plastic concretes. To this end, data were collected from different sources and data gaps were covered by extra experimental tests and finally, 387 data for compressive strength and 107 data for splitting tensile strength were gathered for modeling. This study shows that ANN-PSO is superior to SVM-PSO and ANFIS-PSO in case of predicting compressive as well as splitting tensile strength   of plastic concretes. The coefficient of determination (R2) in case of ANN-PSO for both training and testing sets is more than 0.95. Results of this study can be used to predict the compressive and splitting tensile strength of plastic concretes with regards to constituent materials and specimen geometry of plastic concrete.