Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran

The identification of landslide-prone areas is an essential step in landslide hazard assessment and mitigation of landslide-related losses.In this study,we applied two novel deep learning algorithms,the recurrent neural network(RNN)and convolutional neural network(CNN),for national-scale landslide susceptibility mapping of Iran.We prepared a dataset comprising 4069 historical landslide locations and 11 conditioning factors(altitude,slope degree,profile curvature,distance to river,aspect,plan curvature,distance to road,distance to fault,rainfall,geology and land-sue)to construct a geospatial database and divided the data into the training and the testing dataset.We then developed RNN and CNN algorithms to generate landslide susceptibility maps of Iran using the training dataset.We calculated the receiver operating characteristic(ROC)curve and used the area under the curve(AUC)for the quantitative evaluation of the landslide susceptibility maps using the testing dataset.Better performance in both the training and testing phases was provided by the RNN algorithm(AUC=0.88)than by the CNN algorithm(AUC=0.85).Finally,we calculated areas of susceptibility for each province and found that 6%and 14%of the land area of Iran is very highly and highly susceptible to future landslide events,respectively,with the highest susceptibility in Chaharmahal and Bakhtiari Province(33.8%).About 31%of cities of Iran are located in areas with high and very high landslide susceptibility.The results of the present study will be useful for the development of landslide hazard mitigation strategies.     

Precise Seismic Substructural Model of the Eocene Chorgali Limestone in the Turkwal Oil Field, Central Potwar, Pakistan

The precise seismic substructural interpretation of the Turkwal oil field in the Central Potwar region of district Chakwal of Pakistan has been carried out. The research work was confined to the large fore-thrust that serves as an anticlinal structural trap through ten 2D seismic lines. A precise seismic substructural model of the Eocene Chorgali Limestone with precise orientation of thrust and oblique slip faults shows the presence of a huge fracture, which made this deposit a good reservoir. The abrupt surface changes in dip azimuth for the Eocene Chorgali Limestone verifies the structural trends and also the presence of structural traps in the Turkwal field. The logs of three wells (Turkwal deep X-2, Turkwal-01 and Fimkassar-01) were analyzed for petrophysical studies, well synthetic results and generation of an Amplitude Versus Offset (AVO) model for the area. The AVO model of Turkwal deep X-2 shows abrupt changes in amplitude, which depicts the presence of hydrocarbon content. Well correlation technique was used to define the overall stratigraphic setting and the thickness of the reservoir formation in two wells, Turkwal-01 and Turkwal deep X-2. The Eocene Chorgali Limestone in Turkwal-01 is an upward thrusted anticlinal structure and because of the close position of both wells to the faulted anticlinal structure, its lesser thickness differs compared to Turkwal deep X-2. The overall results confirm that the Turkwal field is comparable to several similar thrust-bound oil-bearing structures in the Potwar basin.     

伊朗锡斯坦地区沙漠灾害区划(英文)

Desertification process as a great problem affects most of the countries in the world.This process has a high rate in arid and semiarid areas.Today,human societies are encountering the desertification phenomenon as a serious problem which causes various irreparable damages to economic and social sectors.In order to assess desertification results in production of different regional models for their application in another region the indices should be re-investigated and adjusted to local conditions.Several models have been developed for desertification evaluation.The present study,attempts to assess quantitatively the desertification process has in an area located at Sistan plain of Iran(Niatak region as a case study) by using Modified MEDALUS method.The obtained results indicated that of the whole studied region(comprising 4819.6 acres),2651.56 acres(55%) are located in medium desertification intensity class,1269.48 acres(26.34%) are positioned in severe desertification intensity class,and 898.54 acres(18.64%) are placed in vary severe desertification intensity class.     

Germination and seedling growth of corn (Zea mays l.) under varying levels of copper and zinc

The heavy metal tolerance in corn (Zea mays L.) var. ‘Neelum’ was assessed at germination and seedling growth after having subjected it to different concentrations of CuSO₄ and ZnSO₄. Germination was not affected by any of the metal tested, whereas initial growth was strongly inhibited by increasing concentrations of ZnSO₄. Seedlings developed toxicity symptoms in the presence of both metals but more chlorotic and necrotic regions were observed at varying levels of ZnSO₄ than CuSO₄. The metal accumulation was concentration dependent. Z. mays seedlings accumulated more copper in roots but greater contents of zinc in their shoots. On the basis of results presented here, it can be concluded that the cultivar of the species tested has shown a marked sensitivity to the presence of small amounts of metals present in the growth medium. The data support the assumption that metal sensitivity is probably due to strong tendency of the species to accumulate them. This justifies that the corn variety ‘Neelum’ is not suitable for the cultivation under situations where water and soil suffer from occasional and/ or transitory metal pollution.