Land use/land cover (LULC) mapping and change detection are fundamental aspects of remote sensing data application. Therefore, selecting an appropriate classifier approach is crucial for accurate classification and ch...Land use/land cover (LULC) mapping and change detection are fundamental aspects of remote sensing data application. Therefore, selecting an appropriate classifier approach is crucial for accurate classification and change assessment. In the first part of this study, the performance of machine learning classification algorithms was compared using Landsat 9 image (2023) of the Manouba government (Tunisia). Three different classification methods were applied: Maximum Likelihood Classification (MLC), Support Vector Machine (SVM), and Random Trees (RT). The classification aimed to identify five land use classes: urban area, vegetation, bare area, water and forest. A qualitative assessment was conducted using Overall Accuracy (OA) and the Kappa coefficient (K), derived from a confusion matrix. The results of the land cover classification demonstrated a high level of accuracy. The SVM method exhibited the best performance, with an overall accuracy of 93% and a kappa accuracy of 0.9. The ML method is the second-best classifier with an overall accuracy of 92% and a kappa accuracy of 0.88. The Random Trees method yielded the lowest accuracy among the three approaches, with an overall accuracy of 91% and a kappa accuracy of 0.87. The second part of the study focused on analyzing LULC changes in the study area. Based on the classification results, the SVM method was chosen to classify the Landsat 7 image acquired in 2000. LULC changes from 2000 to 2023 were investigated using change detection comparison. The findings indicate that over the last 23 years, vegetation land and urban areas in the study area have experienced significant increases of 31.94% and 5.47%, respectively. This study contributed to a better understanding of the classification process and dynamic LULC changes in the Manouba region. It provided valuable insights for decision-makers in planning land conservation and management.展开更多
Groundwater is considered as the main portion of the water supply in arid and semi-arid regions. The Sfax plain area is part of the arid/semi-arid areas of Tunisia that are subject to the impact of climatic and human ...Groundwater is considered as the main portion of the water supply in arid and semi-arid regions. The Sfax plain area is part of the arid/semi-arid areas of Tunisia that are subject to the impact of climatic and human pressures. Water scarcity in combination with groundwater exploitation is a major concern in this region. Therefore, sustainable management and protection of groundwater resources, it necessary. The delineation of groundwater potential (GP) zones becomes an increasingly important tool for implementing successful management programs. The purpose of the present paper is to assess the potential zone of groundwater resources in the study area. An efficient approach using geographical information system (GIS), hydrological modelling and analytical hierarchy process (AHP) was developed. At first, six groundwater parameters that affect groundwater occurrences are derived from the spatial geodatabase. Those parameters are: Infiltration rate estimated from a GIS linked model, lineament density, drainage density, slope, rainfall and Land use/land cover. Then, the assigned weights of thematic layers based on expert knowledge were normalized by eigenvector technique of AHP. The parameter layers were integrated and modeled using a weighted linear combination (WLC). The resulting map was classified into four categories: very low, low, good, and excellent. The results showed that about 26% of the study area falls under very-low-potential zone, with 30% on low-potential zone, 21% with good potential zone, and 23% falling under excellent zone. The results of the analysis were validated using pumping rate data and curve trend of sensitivity classes theory validation of outcomes indicated a good prediction accuracy. The results of the present study can serve to prepare a comprehensive groundwater development and management plans proving its efficacy in this art of exploratory investigations.展开更多
In Tunisia and particularly in Monastir region, groundwater constitutes the main source of water supply systems. A lot of problems are facing the water management authorities. In fact, the Moknine coastal aquifer high...In Tunisia and particularly in Monastir region, groundwater constitutes the main source of water supply systems. A lot of problems are facing the water management authorities. In fact, the Moknine coastal aquifer highlights several qualitative and quantitative anomalies due to the irrigated perimeters extension (Teboulba, Bekalta), releases of harmful products from the textile industry (Ksar Hellal and Moknine), intense overexploitation and seawater intrusion. Thus, for groundwater resources management, a Decision Support System (DSS) is developed for the Monastir region. This Decision Support System (DSS) brings together, on a digital support, the data descriptive and graphical component for groundwater management. It is a hydrogeological relational database joined with a Hydrogeological Information System for the Monastir region (HISM) which enables fast and effective processing of large volumes of spatial data from multiple sources. The implementation of the Hydrogeological Information System is assured using Object-Oriented Programming (OOP). The “Unified Modeling Language” (UML) is an Object-Oriented Design (OOD) methodology which is choiced for data modeling. The application interfaces have been developed in Visual Basic (VB.net) within the Integrated Development Environment (IDE) from Microsoft Visual Studio. “DotSpatial” library integrated is used to manage the geographic information layers. The HISM contains thematic layers acquired through the vectorization of 22 topographic and geologic maps (1/50,000 and 1/25,000) and the input of descriptive data from water well and pollution sources from field and laboratory studies. The HISM has a great management capacity;it ensures the conversion from the geographic coordinates to the planimetric coordinates. It allows adding, modifying, deleting and editing data (Rainfall, piezometric and geochemical). It also ensures the storage and editing of the digitized and/or generated cartographic database. This DSS was applied to the superficial coastal aquifer system of Moknine to define a conceptual model of groundwater functioning and assessment vulnerability to seawater intrusion.展开更多
文摘Land use/land cover (LULC) mapping and change detection are fundamental aspects of remote sensing data application. Therefore, selecting an appropriate classifier approach is crucial for accurate classification and change assessment. In the first part of this study, the performance of machine learning classification algorithms was compared using Landsat 9 image (2023) of the Manouba government (Tunisia). Three different classification methods were applied: Maximum Likelihood Classification (MLC), Support Vector Machine (SVM), and Random Trees (RT). The classification aimed to identify five land use classes: urban area, vegetation, bare area, water and forest. A qualitative assessment was conducted using Overall Accuracy (OA) and the Kappa coefficient (K), derived from a confusion matrix. The results of the land cover classification demonstrated a high level of accuracy. The SVM method exhibited the best performance, with an overall accuracy of 93% and a kappa accuracy of 0.9. The ML method is the second-best classifier with an overall accuracy of 92% and a kappa accuracy of 0.88. The Random Trees method yielded the lowest accuracy among the three approaches, with an overall accuracy of 91% and a kappa accuracy of 0.87. The second part of the study focused on analyzing LULC changes in the study area. Based on the classification results, the SVM method was chosen to classify the Landsat 7 image acquired in 2000. LULC changes from 2000 to 2023 were investigated using change detection comparison. The findings indicate that over the last 23 years, vegetation land and urban areas in the study area have experienced significant increases of 31.94% and 5.47%, respectively. This study contributed to a better understanding of the classification process and dynamic LULC changes in the Manouba region. It provided valuable insights for decision-makers in planning land conservation and management.
文摘Groundwater is considered as the main portion of the water supply in arid and semi-arid regions. The Sfax plain area is part of the arid/semi-arid areas of Tunisia that are subject to the impact of climatic and human pressures. Water scarcity in combination with groundwater exploitation is a major concern in this region. Therefore, sustainable management and protection of groundwater resources, it necessary. The delineation of groundwater potential (GP) zones becomes an increasingly important tool for implementing successful management programs. The purpose of the present paper is to assess the potential zone of groundwater resources in the study area. An efficient approach using geographical information system (GIS), hydrological modelling and analytical hierarchy process (AHP) was developed. At first, six groundwater parameters that affect groundwater occurrences are derived from the spatial geodatabase. Those parameters are: Infiltration rate estimated from a GIS linked model, lineament density, drainage density, slope, rainfall and Land use/land cover. Then, the assigned weights of thematic layers based on expert knowledge were normalized by eigenvector technique of AHP. The parameter layers were integrated and modeled using a weighted linear combination (WLC). The resulting map was classified into four categories: very low, low, good, and excellent. The results showed that about 26% of the study area falls under very-low-potential zone, with 30% on low-potential zone, 21% with good potential zone, and 23% falling under excellent zone. The results of the analysis were validated using pumping rate data and curve trend of sensitivity classes theory validation of outcomes indicated a good prediction accuracy. The results of the present study can serve to prepare a comprehensive groundwater development and management plans proving its efficacy in this art of exploratory investigations.
文摘In Tunisia and particularly in Monastir region, groundwater constitutes the main source of water supply systems. A lot of problems are facing the water management authorities. In fact, the Moknine coastal aquifer highlights several qualitative and quantitative anomalies due to the irrigated perimeters extension (Teboulba, Bekalta), releases of harmful products from the textile industry (Ksar Hellal and Moknine), intense overexploitation and seawater intrusion. Thus, for groundwater resources management, a Decision Support System (DSS) is developed for the Monastir region. This Decision Support System (DSS) brings together, on a digital support, the data descriptive and graphical component for groundwater management. It is a hydrogeological relational database joined with a Hydrogeological Information System for the Monastir region (HISM) which enables fast and effective processing of large volumes of spatial data from multiple sources. The implementation of the Hydrogeological Information System is assured using Object-Oriented Programming (OOP). The “Unified Modeling Language” (UML) is an Object-Oriented Design (OOD) methodology which is choiced for data modeling. The application interfaces have been developed in Visual Basic (VB.net) within the Integrated Development Environment (IDE) from Microsoft Visual Studio. “DotSpatial” library integrated is used to manage the geographic information layers. The HISM contains thematic layers acquired through the vectorization of 22 topographic and geologic maps (1/50,000 and 1/25,000) and the input of descriptive data from water well and pollution sources from field and laboratory studies. The HISM has a great management capacity;it ensures the conversion from the geographic coordinates to the planimetric coordinates. It allows adding, modifying, deleting and editing data (Rainfall, piezometric and geochemical). It also ensures the storage and editing of the digitized and/or generated cartographic database. This DSS was applied to the superficial coastal aquifer system of Moknine to define a conceptual model of groundwater functioning and assessment vulnerability to seawater intrusion.
