Mapping the forest fire risk zones using artificial intelligence with risk factors data.

Geographical information system data has been used in forest fire risk zone mapping studies commonly. However, forest fires are caused by many factors, which cannot be explained only by geographical and meteorological reasons. Human-induced factors also play an important role in occurrence of forest fires, and these factors depend on various social and economic conditions. This article aims to prepare a fire risk zone map by using a data set consisting of 11 human-induced factors, a natural factor, and temperature, which is one of the risk factors that determine the conditions for the occurrence of forest fires. Moreover, k-means clustering algorithm, which is an artificial intelligence method, was employed in preparation of the fire risk zone map. Turkey was selected as the study area because there are social and economic variations among its regions. Thus, the regional forest directorates in Turkey were separated into four clusters as extreme-risk zone, high-risk zone, moderate-risk zone, and low-risk zone. Also, a map presenting these risk zones were provided. The map reveals that, in general, the western and southwestern coastal areas of Turkey are at high risk of forest fires. On the other hand, the fire risk is relatively low in the northern, central, and eastern areas.

Flood vulnerability level analysis as a hydrological disaster mitigation effort in Krueng Jreue Sub-Watershed, Aceh Besar, Indonesia.

The flood phenomenon in the Krueng Jreue Sub-Watershed, Aceh Besar, Indonesia, in recent years indicates biophysical damage to the land. Floods are influenced by factors from biophysical conditions of the land and high rainfall with small river cross-sectional capacity causing water to overflow the embankment and flood low areas. This research aims to analyse the flood vulnerability level in the Krueng Jreue Sub-Watershed, Aceh Besar, Indonesia. The results showed that flood vulnerability in the research area consisted of four classes: very vulnerable, vulnerable, moderately vulnerable and somewhat vulnerable, with each area averaging a score of 43.0, 38.8, 30.0 and 21.7. Types of land use that are particularly vulnerable to flooding are rice fields with a mean total score of 43.0. The vulnerable classes are found in settlements and moorings, with a total score of 42.0 and 36.5, respectively. While open land, shrubs, grasslands, primary forests and secondary forests are quite vulnerable to flooding, with a mean total score of 32.5 each: 30.0, 30.0, 28.0 and 27.0. The main components affecting flood vulnerability are rainfall, temperature and land use, while additional components are soil infiltration and slope. Mechanised hydrological disaster mitigation can be performed through optimisation of weir, embung, rorak and check-dam. Vegetative hydrological mitigation efforts can be performed by reforestation and agroforestry systems, maps and flood prediction. Non-technically, hydrological disaster mitigation efforts can be undertaken with legal policies, law enforcement, map creation and prediction of droughts and socialisation of legislation.

Impact of Novel Incorporation of CT-based Segment Mapping into a Conjugated Gradient Algorithm on Bone SPECT Imaging: Fundamental Characteristics of a Context-specific Reconstruction Method.

OBJECTIVES: The latest single-photon emission computed tomography (SPECT)/computed tomography (CT) reconstruction system, referred to as xSPECT Bone™, is a context-specific reconstruction system utilizing tissue segmentation information from CT data, which is called a zone map. The aim of this study was to evaluate the effects of zone-map enhancement incorporated into the ordered-subset conjugated gradient minimization (OSCGM) reconstruction method on SPECT images. METHODS: Image quality with zone-map enhanced OSCGM (OSCGMz) and non-enhanced OSCGM methods was compared using various reconstruction parameters. The compartment phantom had 3 radioactive sections with CT values of about 1000, 250, and 0 HU. SPECT data were acquired using a low-energy high-resolution (LEHR) collimator, with a 256×256 matrix and 2.4-mm pixel size. The performances of the 2 reconstruction methods (OSCGM vs. OSCGMz) were evaluated on the basis of %error, coefficient of variation (%CV), and normalized mean squared error (NMSE), and adequate iterative update numbers were determined. The relative CV representing the ratio of smoothed images to non-smoothed images was calculated to evaluate the effects of the Gaussian filter on each section set with different CT values. RESULTS: On comparing the OSCGM and OSCGMz methods, it was found that the %error of the OSCGMz method tended to show convergence with fewer updates, especially in the high CT value section mimicking bone absorption. In the water section, the %CV of the OSCGMz method was lower than that of the OSCGM method. The NMSE minimum values for the OSCGM and OSCGMz methods were obtained at 30 and 20 updates, respectively. The relative CV for the OSCGMz method in the water section decreased remarkably according to the size of the full width at half maximum (FWHM) of the Gaussian filter. CONCLUSION: The zone-map enhancement contributed to SPECT reconstruction for the reproduction of radioactive concentrations in bone tissues, using a low number of OSCGM updates. Our findings indicated that the incorporation of zone maps into SPECT reconstruction might improve image quality.