Wildfire Risk in Italy

The risk map

Three Regions Account for 65% of Italy's Modeled Expected Annual Loss

The Italy wildfire risk map contains 388,058 reporting cells. For each cell, SWIM estimates how often a fire is expected to start, how large it could become, and the economic consequences. Ignition frequency is estimated from mapped fire perimeters and generalized across locations with similar conditions. On geographically held-out areas, the model assigns a higher burn probability to a burned cell than to an unburned cell 92 percent of the time. Expected loss combines three modeled components: structures and human safety, land-related losses, and fire-suppression costs.

Italy accounts for approximately 14 percent of modeled EU expected annual wildfire loss and 12 percent of expected annual burned area, ranking third among the 27 member states by expected loss on the European wildfire risk map. The Italian model includes 57,524,092 people and 11,079,966 occupied dwellings in reporting cells containing burnable vegetation. Figure 1 shows the modeled loss by reporting cell.

Expected loss in a reporting cellBelow the medianThe median or more5.9 times the median or more35 times the median or moreThe top 3%

From 2019 through 2025, EFFIS mapped an average of 1,316 fires and 83,548 hectares burned per year in Italy, more fires than in any other member state. Approximately 73 percent of burned area occurred in July and August, with July as the peak month nationally. Italy also has a distinct regional pattern. South of 44°N, where 97 percent of the mapped burned area occurs, fire activity peaks in summer. North of 44°N, including the Alps, Prealps, and Po Valley, fire activity peaks in March before spring green-up, as it does across temperate Europe. The largest individual fires in the Italian EFFIS record include:

• Bonarcado (Montiferru), Sardinia, July 2021: 13,278 ha
• San Mauro Castelverde, Palermo, August 2021: 9,778 ha
• San Lorenzo (Aspromonte), Reggio Calabria, August 2021: 7,096 ha
• Bivona, Agrigento, July 2026: 6,516 ha
• Custonaci, Trapani, July 2025: 5,542 ha

SWIM estimates approximately €426 million in expected annual wildfire loss in Italy, equivalent to about €7,000 per modeled hectare burned.

Sicilia (€143 million), Calabria (€92 million), and Campania (€43 million) together account for approximately 65 percent of Italy's modeled expected annual wildfire loss. Sicilia has the highest expected burned area, while Lombardia has the largest number of homes in the modeled interface. These differences show why burned area and exposure should be evaluated separately. Table 1 lists all 20 regions, and Figure 2 compares the three measures.

The model

SWIM Uses Published European Fuel Maps

SWIM uses the FIRE-RES pan-European surface-fuel layer and the FirEUrisk fuel map, refined with ESA WorldCover and Copernicus tree-cover data. These inputs are mapped to the Scott and Burgan fuel classification used by the spread model and carried onto SWIM's 20-meter hexagons. Fire spread is calculated using the Rothermel and Albini equations across all forty published fuel models. European weather inputs come from ERA5 and CERRA reanalyses for the historical record and ECMWF and ICON-EU forecasts for live requests. Calibration uses the European historical fire record.

Fire-Size Estimates

Fire Size Is Represented as a Range of Possible Outcomes

Because final fire size is uncertain, SWIM estimates a range of possible outcomes rather than a single deterministic value. The model is developed using 156,080 European fire records and evaluated on geographically separate areas that were excluded from training.

For each request, SWIM uses the ignition location, time of year, surrounding fuel, terrain, and settlement, the day's weather, and the local temperature climate to estimate fire size and consequences. Results are reported in hectares and euros and are based on European data.

Fire-Size Validation

Testing the 90th-Percentile Fire-Size Estimate

The 90th-percentile estimate represents a final fire size that about 90 percent of observed fires are not expected to exceed, while about 10 percent are expected to exceed it.

Across 15,360 observed European fires of at least 30 hectares, 90.0 percent of final fire sizes fell at or below the model's 90th-percentile estimate. Across the prediction range, coverage remained within 2.2 percentage points of the 90 percent target, for fires forecast at both 140 hectares and 2,700 hectares.

The model was evaluated using five-fold geographic cross-validation. The EU study area was divided into 379 blocks measuring 100 km by 100 km and assigned to five groups. In each round, one group was excluded from training and used only for evaluation. As a result, every historical fire was tested using a model that had not been trained on fires from the same geographic block. This separation reduces the risk that nearby fires with similar fuel, terrain, and weather make the model appear more accurate simply because it has already seen the same landscape.

Table 2 reports the performance of the 90th-percentile fire-size estimate across the full population. Figure 3 compares eight fires with their modeled ranges, and Table 3 presents their values.

Table 2. Performance of the 90th-percentile fire-size estimate on geographically held-out fires. Overall, 90.0 percent of observed fires fell at or below the modeled 90th percentile. Each fire was evaluated by a model that excluded its entire 100 km block from training.

Table 3. Modeled median and 90th-percentile fire sizes compared with observed final burned area for the eight examples in Figure 3. The start point identifies where each fire simulation began. Each estimate comes from a model that excluded the fire's 100 km geographic block from training. Observed burned area is the area recorded by EFFIS.

The eight fires come from eight member states, from the Portuguese interior and the mountains of León to Crete, Sicily and the southern Carpathians. Three were started where the fire agency recorded the ignition and five where satellites first saw them.

Historical Reconstructions

Historical Fire Reconstructions

Seven fires in this report are Italian. The Ragusa fire of August 2021 appears in the fire-size comparison above, with 1,868 observed hectares against a 90th-percentile estimate of 1,987 hectares. Six additional fires are evaluated spatially using the same workflow as a live request and the weather observed on the day of ignition: the Custonaci fire of July 2025, the fifth largest in the Italian EFFIS record, and fires in Sardinia, near Palermo, Enna and Caltanissetta, and above Calabria's Ionian coast.

Each reconstruction begins at the earliest satellite detection so the model does not use information about the fire's eventual extent. This setup approximates the information available early in an incident: location, landscape conditions, date, and weather. Starting from a point inside the final burned area would introduce information about where the fire ultimately spread. Using the earliest satellite detection therefore keeps the reconstruction closer to a forward-looking test.

The primary spatial metric is the percentage of the observed burn contained within the modeled area. For planning applications, missed portions of the final burn fall outside the modeled planning area. Each fire is first evaluated using its 90th-percentile modeled size and, if the observed fire exceeds that range, also at the 95th percentile. These percentiles are reference points within a continuous modeled distribution, not maximum possible fire sizes. Table 4 presents the inputs, Figure 4 shows the reconstructions, and Table 5 presents their values.

Table 4. Inputs used for the historical fire reconstructions. Each simulation begins at the earliest satellite detection, taken as the center of that overpass rather than a single pixel, and uses observed weather for the day of the fire. The modeled area is drawn using the same rule applied to a live request.

Observed burn: 5,542 ha95th-percentile modeled area: 11,712 ha

Observed burn: 1,170 ha90th-percentile modeled area: 2,081 ha

Observed burn: 1,359 ha90th-percentile modeled area: 2,635 ha

Observed burn: 1,034 ha90th-percentile modeled area: 1,786 ha

Observed burn: 1,409 ha90th-percentile modeled area: 2,450 ha

Observed burn: 848 ha95th-percentile modeled area: 870 ha

The white line shows the observed fire perimeter, and the blue area shows the modeled area beginning from the earliest satellite detection. All six examples were generated using the same model and each fire's observed conditions, without event-specific tuning. Imagery: Esri, Maxar, Earthstar Geographics.

1. aCustonaci, Trapani. The 95th-percentile modeled area captures 99.9 percent of the observed 5,542-hectare burn in western Sicilia.
2. bNuoro, Sardinia. The 90th-percentile modeled area captures 91.3 percent of the observed burn, including most of the two-lobed perimeter while missing part of the southern edge.
3. cMonreale, Palermo. The 90th-percentile modeled area captures 99.1 percent of the observed burn and broadly follows its eastern edge.
4. dPiazza Armerina, Enna. The 90th-percentile modeled area captures 99.8 percent of the observed burn, including the primary north-south spread and western extension.
5. eSutera, Caltanissetta. The 90th-percentile modeled area captures 99.9 percent of the observed burn.
6. fGioiosa Ionica, Reggio Calabria. The 95th-percentile modeled area captures 89.6 percent of the observed burn, missing part of the northern extension.

Table 5. Six historical fire reconstructions beginning from each fire's earliest satellite detection. First sighting identifies the simulation start point, modeled percentile identifies the level of the distribution used, modeled area is the area estimated at that level, and observed burn captured is the share of the mapped perimeter contained within the modeled area.

The comparison

Fire Danger and Long-Term Wildfire Risk Answer Different Questions

EFFIS publishes the Canadian Fire Weather Index (FWI) across Europe each day at about 8 km resolution as an indicator of fire-weather severity. SWIM instead estimates long-term wildfire risk by combining fire likelihood, fire behavior, exposure, and consequence. Both identify the Mediterranean as an important area of wildfire concern, but they measure different quantities.

The Fire Weather Index describes how conducive current weather conditions are to fire. SWIM's national risk map estimates where wildfire risk is concentrated over many years and the expected consequences of burning, while a live request estimates the potential behavior and consequences of a specific fire under current conditions. A location can therefore have a high fire-weather rating but relatively low long-term expected loss if exposure is limited, or the reverse. For example, the same very high FWI rating in a Finnish bog and a Portuguese eucalyptus interface corresponds to SWIM risk estimates that differ by two orders of magnitude because their exposure and expected consequences differ.

Provenance

What the model is built from

Table 6 lists the published European sources used by the model.

Table 6. Model inputs, the organization publishing each source, and the applicable license.