Semi-Automatic Fracture Mapping Using Cellular Neural Networks Applied to ALOS PALSAR 2 Images of the Western Highlands of Cameroon

In Cameroon in general and in the Highlands of Cameroon in particular, there is no fracture map since its realization is not easy. The region’s harsh accessibility and climatic conditions make it difficult to carry out geological prospecting field missions that require large investments. This study proposes a semi-automatic lineament mapping approach to facilitate the elaboration of the fracture map in the West Cameroon Highlands. It uses neural networks in tandem with PCI Geomatica’s LINE algorithm to extract lineaments semi-automatically from an ALOS PALSAR 2 radar image. The cellular neural network algorithm of Lepage et al (2000) is implemented to enhance the pre-processed radar image. Then, the LINE module of Geomatica is applied to the enhanced image for the automatic extraction of lineaments. Finally, a control and a validation of the expert by spatial analysis allows elaborating the fracture map. The results obtained show that neural networks enhance and facilitate the identification of lineaments on the image. The resulting map contains more than 1800 fractures with major directions N20° - 30°, NS, N10° - 20°, N50° - 60°, N70° - 80°, N80° - 90°, N100° - 110°, N110° - 120° and N130° - 140° and N140° - 150°. It can be very useful for geological and hydrogeological studies, and especially to inform on the productivity of aquifers in this region of high agro-pastoral and mining interest for Cameroon and the Central African sub-region.

Effects of climate change on potential habitats of the cold temperate coniferous forest in Yunnan province, southwestern China

We built a classification tree （CT） model to estimate climatic factors controlling the cold temperate coniferous forest （CTCF） distributions in Yunnan province and to predict its potential habitats under the current and future climates, using seven climate change scenarios, projected over the years of 2070-2099. The accurate CT model on CTCFs showed that minimum temperature of coldest month （TMW） was the overwhelmingly potent factor among the six climate variables. The areas of TMW〈-4.05 were suitable habitats of CTCF, and the areas of -1.35 〈 TMW were non-habitats, where temperate conifer and broad-leaved mixed forests （TCBLFs） were distribute in lower elevation, bordering on the CTCF. Dominant species of Abies, Picea, and Larix in the CTCFs, are more tolerant to winter coldness than Tsuga and broad-leaved trees including deciduous broad-leaved Acer and Betula, evergreen broad- leaved Cyclobalanopsis and Lithocarpus in TCBLFs. Winter coldness may actually limit the cool-side distributions of TCBLFs in the areas between -1.35℃ and -4.05℃, and the warm-side distributions of CTCFs may be controlled by competition to the species of TCBLFs. Under future climate scenarios, the vulnerable area, where current potential （suitable ＋ marginal） habitats （80,749 km^2） shift to non-habitats, was predicted to decrease to 55.91% （45,053 km^2） of the current area. Inferring from the current vegetation distribution pattern, TCBLFs will replace declining CTCFs. Vulnerable areas predicted by models are important in determining priority of ecosystem conservation.