Search

Fire effects consist not only in direct damage to the vegetation but also in the modification of both chemical and physical soil properties. Fire can affect the alteration of soil properties in different ways depending on fire severity and soil type. The most important consequences concern changes in soil responsiveness to the water action and the subsequent increase in sediment transport and erosion. Post fire soil loss can increase in the first year by several orders of magnitude compared to pre-fire erosion. In this study a distributed model based on the Revised Universal Soil Loss Equation (RUSLE) is used to estimate potential post-fire soil loss for four different fire events occurred in Basilicata region in 2017. Geographic Information System techniques and remote sensing data have been adopted to build a prediction model of post-fire soil erosion risk. Results show that this model is not only able to quantify post-fire soil loss but also to identify the complexity of the relationships between fire severity and all the factors that influence soil susceptibility to erosion.

Fires represents one of the main causes of environmental degradation and have an important negative impact on the landscape. Fires, in fact, strongly influenced ecological processes and compromise the ecosystems. Measurements of the post-fire damage levels over burned areas are important to quantify fire's impact on landscapes. Remote sensing and geo-statistical approaches are useful tools for the monitoring and analysis of burned areas on a regional scale, because provides reliable and rapid diagnosis of burned areas. Spatial autocorrelation statistics, such as Moran's I and Getis-Ord Local Gi index, were also used to measure and analyze dependency degree among spectral features of burned areas. This approach improves characterization of a burnt area and improves the estimate of the severity of the fire. This paper provides an application of fire severity studies describing post-fire spectral responses of fire affected vegetation to obtain a burned area map. The aim of this work is to implement a procedure, using ESA Sentinel 2 data and spatial autocorrelation statistics in a GIS open-source environment, a graphical model that analyzes the change detection of the potential burned area, as case of study Northern part of Apulia Region (Italy) was used. The burned area was delineated using the spectral indices calculated using Sentinel two images in the period July-August 2020 and using also the land use map of the area.

Soil degradation is a phenomenon that describes the degradation of soil quality due to which agricultural land in particular is unproductive as a consequence of the loss of ability to produce crops and biomass. The causes are many but, especially in the inland areas of the Mediterranean regions, some dynamics related to agriculture have particularly influenced the grading process. Specifically, agricultural over exploitation with unsustainable practices and land abandonment are causing ecological alterations that require contextual analysis to assess the medium and long-term effects. The aim of this work is to investigate the role of some factors that make up the RUSLE index have in the detection and monitoring of potentially degraded areas. In particular, the areas cultivated with arable crops were chosen as the area to be analyzed, because the average annual rate of soil erosion (A factor in RUSLE equation) is high despite the presence of vegetation cover and shown evident problems due to the phenomenon of degradation. In order to identify the potential degraded areas, two factor of RUSLE index have been correlated: C factor that describes the vegetation cover of the soil and A factor which represent the amount of potential soil erosion. All methodologies have been applied in a rural area in the northern part of Basilicata Region (Italy) using GIS and remote sensing approaches, as allows the possibility to perform a series of a complex studies and can be efficiently implemented in environmental monitoring plans.

European Commission in 2009 assessed that in the period 2015–2030 about 11% of agricultural land in the EU are under high potential risk of abandonment due to factors, which has strong and known environmental and socio-economic consequences. The diverse impacts of abandonment need to be addressed via a broader set of policy instruments to alleviate the negative effects or even - reverse the trends in the early stages of the process. The clear identification of abandoned agricultural land is fundamental for a correct mapping for the future management and monitoring of the territories. In this context, this study proposes an innovative method for the detection and mapping of abandoned arable land through the use of remote sensing techniques and geo-statistical analysis. The combined use of Sentinel 2 images and the Landsat constellation, the use of NDVI index and change detection analysis made it possible to identify the change in agricultural use and/or abandonment of land in the eastern part of the Basilicata region in the period 1990–2020. (Italy). All process has been developed integrating Remote Sensing and Geographic Information System (GIS), using open-source software.

The use of plastic materials in agriculture involves several benefits but it results in huge quantities of agricultural plastic waste to be disposed of. Input and output data on the use of plastics in agriculture are often difficult to obtain and poor waste management schemes have been developed. The present research aims to estimate and map agricultural plastic waste by using satellite images. Waste was evaluated by means of the indexes relating waste production to crop type and plastic application as defined by the land use map realized by classifying the Landsat 8 image. The image classification was carried out using Support Vector Machines (SVMs), and the accuracy assessment showed that the overall accuracy was 94.54% and the kappa coefficient equal to 0.934. Data on the plastic waste obtained by the satellite land use map were compared with the data obtained by using the institutional land use map; a difference of 1.74% was identified on the overall quantity of waste.

This paper focuses on the potential of the latest generation of Airborne laser scanning (ALS) for the detection and the spatial characterization of microtopographic relief linked to ancient landscapes and palaeoenvironmental features. ALS is an optical measurement technique for obtaining high-precision information about the Earth's surface including basic terrain mapping (Digital terrain model, bathymetry, corridor mapping), vegetation cover (forest assessment and inventory), coastal, and urban areas. Recent studies examined the possibility of using ALS in archaeological investigations to identify earthworks, although the ability of ALS measurements in this context has not yet been studied in detail. In this study, the investigations based on ALS survey and aerial photos were carried out for the natural protected area, Bosco dell'Incoronata in the Apulia Region (Southern Italy). The investigated area is an important site from the naturalistic, historic and archaeological point of view. It is an ancient lowland forest, still present in the medieval time, which has been characterized by a long and intensive human activity from Neolithic to Middle Ages. The LiDAR based analysis allowed us to identify features not visible from ground or from optical data set because hidden by forest canopy and dense understory. The DTM enabled us to identify some microtopographic relief linked to traces of past landscapes, as in the case of the Cervaro paleaoriverbed. It is quite interesting to note that the river changed many times from North to South side compared to the present stream, and traces of past human activities can be still evident close to the diverse paleaoriverbeds. Nevertheless, intensive and systematic study of the ancient landscapes of the Bosco dell'Incoronata is just beginning and so far questions tend to be raised rather than answered. The current study emphasizes the potential of aerial LiDAR (Light Detection And Ranging) survey for detecting surface discontinuities and microtopographic relief linked to palaeoenvironmental features, even hidden by under dense canopy and understory.

MODIS-NDVI data from 2002 to 2014 were analysed to evaluate the effect of fire on vegetation in a test site located in Daxing'anling region (Inner Mongolia and Heilongjiang Province). Fire-affected and fire-unaffected areas were processed using two statistical approaches: detrended fluctuation analysis (DFA) and Fisher–Shannon (FS) method. The DFA allows the detection of scaling behaviour in nonstationary signals, whereas the FS method permits to identify the organization/order structure in complex signals. Our findings show that the results obtained by jointly using the two methods are consistent, enabling the characterization and discrimination between the fire-affected and fire-unaffected areas. In particular, among the investigated indices, the mean value of Fisher information measure (FIM) represents the most significant in discriminating between burned and unburned sites; its mean value for burned sites is about 2.5 that is significantly larger than that obtained for unburned sites (∼1.3). FIM is also characterized by the larger effectiveness in discriminating the two classes of sites on the base of its receiver operating characteristic based performance. The scaling exponents estimated by means of the DFA of the fire-affected pixels are averagely higher than those of the fire-unaffected ones, which, furthermore, are characterized by lower organization and higher disorder degree. Both of the two methods would contribute to identify the impact of fires on vegetation.

The time dynamics of SPOT-VEGETATION Normalized Difference Vegetation Index (NDVI) time series are analyzed by using the statistical approach of the Fisher–Shannon (FS) information plane to assess and monitor vegetation recovery after fire disturbance. Fisher–Shannon information plane analysis allows us to gain insight into the complex structure of a time series to quantify its degree of organization and order. The analysis was carried out using 10-day Maximum Value Composites of NDVI (MVC-NDVI) with a 1 km × 1 km spatial resolution. The investigation was performed on two test sites located in Galizia (North Spain) and Peloponnese (South Greece), selected for the vast fires which occurred during the summer of 2006 and 2007 and for their different vegetation covers made up mainly of low shrubland in Galizia test site and evergreen forest in Peloponnese. Time series of MVC-NDVI have been analyzed before and after the occurrence of the fire events. Results obtained for both the investigated areas clearly pointed out that the dynamics of the pixel time series before the occurrence of the fire is characterized by a larger degree of disorder and uncertainty; while the pixel time series after the occurrence of the fire are featured by a higher degree of organization and order. In particular, regarding the Peloponneso fire, such discrimination is more evident than in the Galizia fire. This suggests a clear possibility to discriminate the different post-fire behaviors and dynamics exhibited by the different vegetation covers.

Remote sensing fire danger prediction model is applied to Northern China. This study was carried out in the Daxing'anling region, which is located in Heilongjiang Province and Inner Mongolia (50.5 degrees-52.25 degrees N, 122 degrees-125.5 degrees E), the northern China. The method integrated by dead fuel moisture content and relative greenness index, which is based on the fire potential index (FPI), was used to predict the fire danger level of the study area. The case that fire happened on the late June 2010 was used to validate the modified method. The results pointed out that the fire affected areas were located in high fire danger level on 26th, 27th, 28th June, 2010 respectively. The ROC analyses of the predicted accuracy on these days were 90.98 %, 73.79 % and 69.07 % respectively. Results from our investigation pointed out the reliability of the adopted method.

Up to nowadays, satellite data have become increasingly available, thus offering a low cost or even free of charge unique tool, with a great potential for operational monitoring of vegetation cover, quantitative assessment of urban expansion and urban sprawl, as well as for monitoring of land use changes and soil consumption. This growing observational capacity has also highlighted the need for research efforts aimed at exploring the potential offered by data processing methods and algorithms, in order to exploit as much as possible this invaluable space-based data source. The work herein presented concerns an application study on the monitoring of vegetation cover with the use of multi-temporal (2010-2014) satellite Modis data. The selected test site is the Iguazu park highly significant, being it one of the most threatened global conservation priorities (http://whc.unesco.org/en/list/303/). In order to produce synthetic maps of the investigated areas to monitor the status of vegetation and ongoing subtle changes, satellite data were processed using Principal Component Analysis (PCA). Results from our investigations pointed out an ongoing degradation trend.

Over the years, there have been a large number of satellite remote-sensing missions that have been providing enormous amounts of remotely sensed data with continuous improvements in the radiometric...

The characterization of fuel types is very important for computing spatial fire hazard and risk and simulating fire growth and intensity across a landscape. However, due to the complex nature of fuel characteristic a fuel map is considered one of the most difficult thematic layers to build up. The advent of sensors with increased spatial resolution may improve the accuracy and reduce the cost of fuels mapping. The objective of this research is to evaluate the accuracy and utility of imagery from the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) satellite imagery. In order to ascertain how well ASTER data can provide an exhaustive classification of fuel properties a sample area characterized by mixed vegetation covers was analysed. The selected sample areas has an extension at around 60 km2 and is located inside the Sila plateau in the Calabria Region (South of Italy). Fieldwork fuel type recognitions, performed before, after and during the acquisition of remote sensing ASTER data, were used as ground-truth dataset to assess the results obtained for the considered test area. The method comprised the following three steps: (I) adaptation of Prometheus fuel types for obtaining a standardization system useful for remotely sensed classification of fuel types and properties in the considered Mediterranean ecosystems; (II) model construction for the spectral characterization and mapping of fuel types based on a maximum likelihood (ML) classification algorithm; (III) accuracy assessment for the performance evaluation based on the comparison of ASTER-based results with ground-truth. Results from our analysis showed that the use ASTER data provided a valuable characterization and mapping of fuel types being that the achieved classification accuracy was higher than 90%.

Fuel types are one of the most important factors that should be taken into consideration for computing spatial fire hazard and risk and simulating fire growth and intensity across a landscape. However, fuel mapping is extremely difficult because the description of fuel properties is very complex. In the present study, forest fuel mapping is considered from a remote sensing perspective by the assessment and mapping of general vegetation complexes. The purpose is to delineate forest types by exploring the use of remote sensing QuickBird data. In order to ascertain how well QuickBird data can provide an exhaustive classification of fuel properties, a sample area characterized by mixed vegetation covers and complex topography data was analysed. The selected sample area has an extension at around 60 km 2 and is located inside the Sila plateau in the Calabria Region (South of Italy). Fieldwork fuel type recognitions, performed before, after and during the acquisition of remote sensing QuickBird data, were used as ground-truth dataset to assess the results obtained for the considered test area. The method comprised the following three steps: (I) adaptation of Prometheus fuel types for obtaining a standardization system useful for remotely sensed classification of fuel types and properties in the considered Mediterranean ecosystems; (II) model construction for the spectral characterization and mapping of fuel types based on a maximum likelihood (ML) classification algorithm; (III) accuracy assessment for the performance evaluation based on the comparison of QuickBird-based results with ground-truth data. Results from our analysis showed that the use of remotely sensed data at high spatial and spectral resolution provided a valuable characterization and mapping of fuel types being that the achieved classification accuracy was higher than 75%.

In this paper, we present and discuss the investigations we conducted in the context of the MITRA project focused on the use of low cost technologies (data and software) for pre-operational monitoring of land degradation in the Basilicata Region. The characterization of land surface conditions and land surface variations can be efficiently approached by using satellite remotely sensed data mainly because they provide a wide spatial coverage and internal consistency of data sets. In particular, Normalized Difference Vegetation Index (NDVI) is regarded as a reliable indicator for land cover conditions and variations and over the years it has been widely used for vegetation monitoring. For the aim of our project, in order to detect and map vegetation anomalies ongoing in study test areas (selected in the Basilicata Region) we used the Principal Component Analysis applied to Landsat Thematic Mapper (TM) time series spanning a period of 25 years (1985-2011).

The characterization of 1 / f α scaling behaviour in normalized difference vegetation index (NDVI) satellite data of forest ecosystems in southern Italy has been performed using the multiple segmenting method (MSM) and detrended fluctuation analysis (DFA). Our findings point out to the characterization of Mediterranean forest ecosystems as governed by persistent mechanisms, which indicate positive feedbacks tending to destabilize the system under external forces or perturbations.

This study aims to ascertain how well remote sensing data can characterize fuel type at different spatial scales in fragmented ecosystems. For this purpose, multisensor and multiscale remote sensing data such as hyperspectral Multispectral Infrared and Visible Imaging Spectrometer (MIVIS) and Landsat Thematic Mapper (TM) data acquired in 1998 were analysed for a test area in southern Italy characterized by mixed vegetation covers and complex topography. Fieldwork fuel type recognition, performed at the same time as remote sensing data acquisitions, was used to assess the results obtained for the considered test areas. Results from preliminary analysis showed that the use of unmixing techniques allows an increase in accuracy of around 7% compared with the accuracy level obtained by applying a widely used classification algorithm.

This study deals with the use of satellite TM multi-temporal data coupled with statistical analyses to quantitatively estimate urban expansion and soil consumption for small towns in southern Italy. The investigated area is close to Bari and was selected because highly representative for Italian urban areas. To cope with the fact that small changes have to be captured and extracted from TM multi-temporal data sets, we adopted the use of spectral indices to emphasize occurring changes, and geospatial data analysis to reveal spatial patterns. Analyses have been carried out using global and local spatial autocorrelation, applied to multi-date NASA Landsat images acquired in 1999 and 2009 and available free of charge. Moreover, in this paper each step of data processing has been carried out using free or open source software tools, such as, operating system (Linux Ubuntu), GIS software (GRASS GIS and Quantum GIS) and software for statistical analysis of data (R). This aspect is very important, since it puts no limits and allows everybody to carry out spatial analyses on remote sensing data. This approach can be very useful to assess and map land cover change and soil degradation, even for small urbanized areas, as in the case of Italy, where recently an increasing number of devastating flash floods have been recorded. These events have been mainly linked to urban expansion and soil consumption and have caused loss of human lives along with enormous damages to urban settlements, bridges, roads, agricultural activities, etc. In these cases, remote sensing can provide reliable operational low cost tools to assess, quantify and map risk areas.

Traditional methods of recording fire burned areas and fire severity involve expensive and time-consuming field surveys. Available remote sensing technologies may allow us to develop standardized burn-severity maps for evaluating fire effects and addressing post fire management activities. This paper focuses on multiscale characterization of fire severity using multisensor satellite data. To this aim, both MODIS (Moderate Resolution Imaging Spectroradiometer) and ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) data have been processed using geo-statistic analyses to capture pattern features of burned areas. Even if in last decades different authors tried to integrate geo-statistics and remote sensing image processing, methods used since now are only variograms, semivariograms and kriging. In this paper, we propose an approach based on the use of spatial indicators of global and local autocorrelation. Spatial autocorrelation statistics, such as Moran's I and Getis–Ord Local Gi index, were used to measure and analyze dependency degree among spectral features of burned areas. This approach enables the characterization of pattern features of a burned area and improves the estimation of fire severity.

This paper presents the results we obtained in the context of the FIRE-SAT project focused on the use of satellite data for pre-operational monitoring of fire danger and fire effects in the Basilicata Region. The use of satellite data was manyfold, to obtain: (i) fuel property (type and loading) maps, mainly obtained from satellite Landsat TM data, (ii) fuel moisture estimation (mainly from MODIS), (iii) fire danger/susceptibility indices as well as (iv) post fire effects including fire severity and vegetation recovery assessment. Results obtained during the first year of project (2008) suggested that the integrated model identified the main fire danger zones by means of the integration of fuel types with daily fuel moisture and Greenness maps. MODIS multitemporal data analyses enable us to dynamically estimate fire severity as well as to map fire affected areas and evaluate the vegetation recovery capability over time. The pre-operative use of the integrated model, carried out within the framework of the FIRE-SAT project funded by the Basilicata Region, pointed out that the system enables us to timely monitor spatial and temporal variations of fire susceptibility and promptly provide useful information on both fire severity and post fire regeneration capability.

Satellite time series offer great potential for a quantitative assessment of urban expansion, urban sprawl and for monitoring of land use changes and soil consumption. This study deals with the spatial characterization of expansion of urban areas by using spatial autocorrelation techniques applied to multi-date Thematic Mapper (TM) satellite images. The investigation focused on several very small towns close to Bari. Urban areas were extracted from NASA Landsat images acquired in 1976, 1999 and 2009, respectively. To cope with the fact that small changes have to be captured and extracted from TM multi-temporal data sets, we adopted the use of spectral indices to emphasize occurring changes, and spatial autocorrelation techniques to reveal spatial patterns. Urban areas were analyzed using both global and local autocorrelation indexes. This approach enables the characterization of pattern features of urban area expansion and it improves land use change estimation. The obtained results showed a significant urban expansion coupled with an increase of irregularity degree of border modifications from 1976 to 2009.

Satellite remote sensing can successfully cope with different aspects of fire management problems, such as danger estimation, fire detection, burned area mapping and post-fire vegetation recovery. In particular, remote sensing can provide valuable data on type (namely distribution and amount of fuels) and status of vegetation in a consistent way at different spatial and temporal scales. The characterization and mapping of fuel types is one of the most important factors that should be taken into consideration for wildland fire prevention and pre-fire planning. In this paper, we provide a brief overview on the use of satellite data for the characterization and mapping of fuel type. Such research activities are part of the FUELMAP project, funded by JRC and focused on the development of fuel models for European ecosystems.

The dynamics of vegetation covers in burned and unburned areas can be monitored by using satellite data, which provide a wide spatial coverage and internal consistency of data sets. Several indices based on satellite data can be used for this aim. In particular, NDVI (Normalized Difference Vegetation Index) is the most widely used index for vegetation monitoring based on remote sensing. This paper aims to perform a dynamical characterization of burned and unburned vegetation covers, using time series of remotely sensed data of some fire-affected and fire-unaffected sites. For this purpose, we used the Detrended Fluctuation Analysis (DFA), which permits the detection of persistent properties in nonstationary signals. Our results point out that the persistence of vegetation dynamics is significantly increased by the occurrence of fires.

A reliable mapping of fuel types is very important for computing fire hazard and risk and simulating fire growth and intensity across a landscape. Due to the complex nature of fuel characteristic a fuel map is considered one of the most difficult thematic layers to build up especially for large areas. The advent of satellite sensors with increased spatial resolution may improve the accuracy and reduce the cost of fuels mapping. The objective of this research is to evaluate the accuracy and utility of imagery from the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) satellite imagery. In order to ascertain how well ASTER data can provide an exhaustive classification of fuel properties a sample area characterized by mixed vegetation covers was analysed. The selected sample areas has an extension at around 60 km2 and is located inside the Sila plateau in the Calabria Region (South of Italy). Fieldwork fuel type recognitions, performed before, after and during the acquisition of remote sensing ASTER data, were used as ground-truth dataset to assess the results obtained for the considered test area. Results from our analysis showed that the use ASTER data provided a valuable characterization and mapping of fuel types with a classification accuracy higher than 78%.

Fuel types is one of the most important factors that should be taken into consideration for computing spatial fire hazard and risk and simulating fire growth and intensity across a landscape. In the present study, forest fuel mapping is considered from a remote sensing perspective. The purpose is to delineate forest types by exploring the use of coarse resolution satellite remote sensing MODIS imagery. In order to ascertain how well MODIS data can provide an exhaustive classification of fuel properties a sample area characterized by mixed vegetation covers and complex topography was analysed. The study area is located in the South of Italy. Fieldwork fuel type recognitions, performed before, after and during the acquisition of remote sensing MODIS data, were used as ground-truth dataset to assess the obtained results. The method comprised the following three steps: (I) adaptation of Prometheus fuel types for obtaining a standardization system useful for remotely sensed classification of fuel types and properties in the considered Mediterranean ecosystems; (II) model construction for the spectral characterization and mapping of fuel types based on two different approach, maximum likelihood (ML) classification algorithm and spectral Mixture Analysis (MTMF); (III) accuracy assessment for the performance evaluation based on the comparison of MODIS-based results with ground-truth. Results from our analyses showed that the use of remotely sensed MODIS data provided a valuable characterization and mapping of fuel types being that the achieved classification accuracy was higher than 73% for ML classifier and higher than 83% for MTMF.

This study aims to ascertain how well remote sensing data can characterize fuel type at different spatial scales in fragmented ecosystems. For this purpose, multisensor and multiscale remote sensing data such as, hyperspectral (Multispectral Infrared and Visible Imaging Spectrometer) MIVIS and Landsat- Temathic Mapper (TM) acquired in 1998 were analysed for a test area of Southern Italy characterized by mixed vegetation covers and complex topography. Fieldwork fuel type recognition, performed at the same time as remote sensing data acquisitions, were used to assess the results obtained for the considered test areas.. The method comprised the following three steps: (I) adaptation of Prometheus fuel types for obtaining a standardization system useful for remotely sensed classification of fuel types and properties in the considered Mediterranean ecosystems; (II) model construction for the spectral characterization and mapping of fuel types; (III) accuracy assessment for the performance evaluation based on the comparison of satellite-based results with ground-truth. Two different approaches have been adopted for fuel type mapping: the well-established classification techniques and spectral mixture analysis. Results from preliminary analysis have showed that the use of unmixing techniques allows an increase in accuracy at around 7% compared to the accuracy level obtained by applying a widely used classification algorithm.

SPOT-Vegetation (SPOT-VGT) data at full spatial resolution were used in order to assess the potentiality and feasibility of using low resolution optical satellite data for the estimation of time/space dynamics of surface moisture content. The seasonal trend of diverse parameters (single channels or spectral indices) suitable/or specifically designed for moisture estimation have been analyzed in some test sites of southern Italy. The investigations were performed by using imagery selected from a long time series of ten-day compositions of VGT data acquired from 1998 to 2002. The preliminary results indicate that the use of the VGT data for obtaining information on the time/space dynamics of surface moisture content can be useful.

The characterization and mapping of fuel types is one of the most important factors that should be taken into consideration for wildland fire prevention and prefire planning. This research aims to investigate the usefulness of hyperspectral data to recognize and map fuel types in order to ascertain how well remote sensing data can provide an exhaustive classification of fuel properties. For this purpose airborne hyperspectral Multispectral Infrared and Visible Imaging Spectrometer (MIVIS) data acquired in November 1998 have been analyzed for a test area of 60 km2 selected inside Pollino National Park in the south of Italy. Fieldwork fuel-type recognitions, performed at the same time as remote sensing data acquisition, were used as a ground-truth dataset to assess the results obtained for the considered test area. The method comprised the following three steps: 1) adaptation of Prometheus fuel types for obtaining a standardization system useful for remotely sensed classification of fuel types and properties in the considered Mediterranean ecosystems; 2) model construction for the spectral characterization and mapping of fuel types based on a maximum likelihood (ML) classification algorithm; and 3) accuracy assessment for the performance evaluation based on the comparison of MIVIS-based results with ground truth. Results from our analysis showed that the use of remotely sensed data at high spatial and spectral resolution provided a valuable characterization and mapping of fuel types being that the achieved classification accuracy was higher than 90%.