No abstract

Indonesia has experienced extensive land-cover change and frequent vegetation and land fires in the past few decades. We combined a new land-cover dataset with satellite data on the timing and location of fires to make the first detailed assessment of the association of fire with specific land-cover transitions in Riau, Sumatra. During 1990 to 2017, secondary peat swamp forest declined in area from 40,000 to 10,000 km 2 and plantations (including oil palm) increased from around 10,000 to 40,000 km 2 . The dominant land use transitions were secondary peat swamp forest converting directly to plantation, or first to shrub and then to plantation. During 2001-2017, we find that the frequency of fire is greatest in regions that change land-cover, with the greatest frequency in regions that transition from secondary peat swamp forest to shrub or plantation (0.15 km −2 yr −1 ). Areas that did not change land cover exhibit lower fire frequency, with shrub (0.06 km −2 yr −1 ) exhibiting a frequency of fire >60 times the frequency of fire in primary forest. Our analysis demonstrates that in Riau, fire is closely connected to land-cover change, and that the majority of fire is associated with the transition of secondary forest to shrub and plantation. Reducing the frequency of fire in Riau will require enhanced protection of secondary forests and restoration of shrub to natural forest.Remote Sens. 2020, 12, 3 2 of 12 to protected areas [15,16]. Fire is used as part of the land-conversion process, to clear vegetation in preparation for agriculture and plantations [17]. In Riau, Indonesia, fires are six times more frequent in regions experiencing recent tree cover loss compared to regions with no loss [16].Understanding the links between land-cover change and fire is necessary to inform land and fire management and fire suppression efforts. However, there is still poor understanding of the fraction of fire that is associated with specific land-cover changes. Satellite datasets provide some information on land-cover change (i.e., canopy cover loss), but there is rarely detailed information on the specific land-cover transitions that occur. Here we combine a new land-cover dataset with information on the location and timing of fires from satellite, to make the first assessment of the association between fire and specific land-cover transitions in Indonesia. We focus on Riau province, one of the most active areas of fire in Indonesia. Materials and MethodsOur study area consists of the province of Riau, Sumatra, covering 89,691 km 2 and consisting of 43% peatland [16]. We used the land-cover map provided by the Indonesian Ministry of Environment and Forestry the land-cover classification was conducted as a part of National Forest Inventory (NFI) project which predominantly relied on analysis of Landsat imagery. During 2000During -2009 Landsat images were combined with 1000 m SPOT Vegetation and 250 m MODIS images, but the classification still depended on visual image interpretation. Finally, since 2009 only Landsat images have b...

No abstract

No abstract

Utilizing data mining tasks such as classification on spatial data is more complex than those on non-spatial data. It is because spatial data mining algorithms have to consider not only objects of interest itself but also neighbours of the objects in order to extract useful and interesting patterns. One of classification algorithms namely the ID3 algorithm which originally designed for a non-spatial dataset has been improved by other researchers in the previous work to construct a spatial decision tree from a spatial dataset containing polygon features only. The objective of this paper is to propose a new spatial decision tree algorithm based on the ID3 algorithm for discrete features represented in points, lines and polygons. As in the ID3 algorithm that use information gain in the attribute selection, the proposed algorithm uses the spatial information gain to choose the best splitting layer from a set of explanatory layers. The new formula for spatial information gain is proposed using spatial measures for point, line and polygon features. Empirical result demonstrates that the proposed algorithm can be used to join two spatial objects in constructing spatial decision trees on small spatial dataset. The proposed algorithm has been applied to the real spatial dataset consisting of point and polygon features. The result is a spatial decision tree with 138 leaves and the accuracy is 74.72%.

Predicting hotspot occurrence as an indicator of forest and land fires is essential in developing IntroductionPredicting hotspots occurrence is considered as one of activities for fire prevention in order to reduce damages because of forest and land fires. Hotspots (active fires) indicate spatial distribution of forest and land fires. Hotspots occurrence models have been developed in several studies using geographical information systems and remote sensing technologies. In addition, data mining as one of growing areas in computer science has been applied to spatial forest fires datasets to obtain classification models for hotspots occurrence.Decision tree is a famous method for classification tasks and it has been applied to a broad range of applications. Some of decision tree algorithms are ID3, C4.5 as a successor of ID3, and CART (Classification and Regression Tree). These algorithms are designed for nonspatial datasets. The different between spatial and non-spatial decision data is that in the spatial data, an object may have a significant influence on neighboring objects. Therefore, improvement of the non-spatial decision tree algorithm has been done by involving spatial relationships between two spatial objects.Several studies have been conducted on spatial decision tree algorithms. The spatial decision tree algorithm was introduced in [1] based on the ID3 algorithm involving the spatial relationship Distance. The spatial binary tree algorithm was proposed in [2] that works on the dataset containing point, line, and polygon features. An extension of the CART method, called the SCART (Spatial Classification and Regression Trees), was developed in [3]. In the SCART, topological and distance relationships are used to test whether a predictive attribute belongs to the neighbor table.The SCART was applied to analyze traffic risk using accident information and thematic information about road networks, population census, buildings, and other geographic neighborhood details [3]. A spatial decision tree based on the ID3 algorithm that works on polygon features was introduced in [4]. The algorithm was applied to classify the average (per farm) market value of sold agricultural products based on climate, the distribution of the principal aquifers, crops cultivated, and the number of cattle and calves per area. The spatial entropy-based decision tree method was proposed in [5] which uses the spatial relation Distance to relate point and polygon features. The algorithm was used to classify gross values of agricultural output [5] and the air pollution index in main cities in China [6]. A new formula for

Application of data mining techniques in library data results interesting and useful patterns that can be used to improve services in university libraries. This paper presents results of the work in applying the sequential pattern mining algorithm namely AprioriAll on a library transaction dataset. Frequent sequential patterns containing book sequences borrowed by students are generated for minimum supports 0.3, 0.2, 0.15 and 0.1. These patterns can help library in providing book recommendation to students, conducting book procurement based on readers need, as well as managing books layout.

No abstract