Journal of Spatial Analysis

---

Objective: Floods are among the most significant natural disasters in Mazandaran Province, particularly in Sari County, where they cause widespread economic, social, and environmental damages each year. The main objective of this research is to identify and map flood hazard zones using machine learning algorithms, namely Random Forest (RF) and Support Vector Machine (SVM), and to apply an ensemble approach in order to enhance prediction accuracy and reduce model uncertainty.
Method: In this study, a set of spatial datasets including a Digital Elevation Model (DEM), land use/land cover derived from satellite imagery, geomorphological indices (slope, aspect, and drainage density), geological data, distance from roads and streams, vegetation index (NDVI), and climatic variables (precipitation and temperature) were collected. These datasets were processed using GIS and RS techniques and prepared for model training and validation. The models’ performance was assessed using evaluation metrics such as Accuracy, F1-score, AUC, and ROC curve analysis.
Findings: The results indicated that both RF and SVM demonstrated high performance in flood hazard mapping, as reflected by strong evaluation metrics. Moreover, the ensemble approach improved prediction reliability and reduced errors compared to single-model predictions. The generated maps revealed that a significant portion of Sari County falls within high and very high hazard zones, which overlap with are::as char::acterized by intense rainfall, high drainage density, and steep slopes.
Conclusion: This research highlights that machine learning algorithms, particularly when applied in an ensemble framework, are powerful tools for identifying flood-prone areas. The findings can serve as a scientific basis for urban planning, disaster management, and flood risk reduction strategies in Sari County and other comparable regions.
 

---

Changes in ground surface temperature in the city of Halle and its relationship with changes in the NDVI index
abstract
The temperature of the urban environment is one of the parameters that citizens are in contact with at any moment. Studies show that the global temperature is constantly increasing due to environmental changes. One of these parameters that affect the increase in temperature; The physical growth of the city and its consequent destruction and loss of vegetation. In this study, using Landsat satellite images for the years 2001, 2011 and 2021; and the implementation of the single-channel algorithm, the surface temperature of the ground in the Iraqi city of Halla was calculated and its changes were investigated and analyzed. On the other hand, the NDVI index was calculated as a vegetation index on the mentioned dates and its changes were analyzed with the temperature changes of the earth's surface. The general results of this research showed that the area of the city of Halle has doubled during the study period, and this has caused a decrease in the amount of vegetation and an increase in the temperature of the earth's surface. In the end, the correlation between the surface temperature and the NDVI index was calculated, which was equal to 46.92, 44.35 and 52.98% for the years 2001, 2011 and 2021, respectively. This issue shows the strong relationship between these two parameters and the effect of the reduction of vegetation on the increase in the temperature of the earth's surface.

Key words: Earth surface temperature, vegetation, NDVI, city growth, Halle city
 

---

Analysis of occurrence potential of the earth/debris flow and
shallow landslides using the TRIGRS model
(Case study: Babolrood Basin, Mazandaran)
In this study, the occurrence potential of rainfall-induced shallow landslides in the Babolrood basin has been investigated. In this basin, due to the mountainous topography and the presence of loose organic soils, the potential of such landslides is high, and landslides of different sizes occur every year after long and intense rainfalls. These landslides, which start with the sliding mechanism in the upper parts of the soil cover, immediately turn into earth/debris flows, and from their joining together, large flows may form downstream of the basin, which is considered a destructive phenomenon. In this research, to investigate the effect of rainfall on the occurrence of shallow landslides and flows, the TRIGRS program, which is a comprehensive and grid-based program for slope stability analysis using the infinite slope method, has been used. In this program, the effect of rainwater penetration into the soil and runoff caused by rainfall, which are important parameters in the occurrence of shallow landslides and subsequent flows, are also fully considered and this natural phenomenon is fully simulated. The input data required for this research includes topographical data of the basin, geological and hydrogeological properties of soil units, and rainfall data in the region, which are prepared in the form of appropriate text files and GIS maps. The output of the Triggers program includes maps of the spatial distribution of the minimum safety factor, the depth of the failure, and the pore water pressure at the failure depth, which are prepared in the form of text files and can be interpreted in GIS-based software. The results of this study showed that in the high and steep parts of the basin, wherever there are soils on a bedrock rich in clay minerals (such as mudstone, marl, and shale), the potential for shallow rainfall-induced landslides is high. In the field studies, a good agreement between the results of this study and the experiences obtained from field observations of landslides caused by rainfall in the region was obtained in terms of their spatial distribution and time of occurrence.
Keywords: Shallow landslide; Pore pressure; Rainfall-induced landslide