Abrupt changes in environmental temperature, wind and humidity can lead to great threats to human life safety. The Gansu marathon disaster of China highlights the importance of early warning of hypothermia from extremely low apparent temperature (AT). Here a deep convolutional neural network model together with a statistical downscaling framework is developed to forecast environmental factors for 1 to 12 h in advance to evaluate the effectiveness of deep learning for AT prediction at 1 km resolution. The experiments use data for temperature, wind speed and relative humidity in ERA-5 and the results show that the developed deep learning model can predict the upcoming extreme low temperature AT event in the Gansu marathon region several hours in advance with better accuracy than climatological and persistence forecasting methods. The hypothermia time estimated by the deep learning method with a heat loss model agrees well with the observed estimation at 3-hour lead. Therefore, the developed deep learning forecasting method is effective for short-term AT prediction and hypothermia warnings at local areas.

Objective: to achieve accurately and rapidly the mapping of agricultural land use and crop distribution at the township scale. Methods: this study, based on specific methods, such as, time-series remote sensing index threshold classification and maximum likelihood, classifies each land use type and extracts crop spatial information, under the guidance of Sentinel-2A remote sensing images, to carry out agricultural land use mapping at township scale. And the mapping concerned will be verified by comparing with an agricultural spatial information map of a 0.5 m resolution, which is based on WorldVieW-2 fused images. Results: (1) the area accuracy of grain and oil crop land, vegetable land, agricultural facilities land and garden land is fairly good, with 92.93%, 98.98%, 95.71% and 95.14% respectively, and within 8% variation from actual area; (2) the spatial information of plot boundary, farmland road network, and canal network produced by OSM road data and historical high-resolution images was overlayed with the classification results of Sentinel-2A multi-spectral image for mapping, which can improve the accuracy of plot boundary information of classification results for the image with 10 m resolution. Conclusions: the use of multi-source information fusion method, agricultural land use and crop distribution space big data produced by Sentinel-2A optical image, can effectively improve the accuracy and timeliness of land use mapping at the township scale, to provide technical reference for the application of remote sensing big data to carry out agricultural landscape analysis at the township scale, optimization and adjustment of agricultural structure, etc.

This article explored mineral resources and their relation to structural settings in the Central Eastern Desert (CED) of Egypt. Integration of remote sensing (RS) with aeromagnetic (AMG) data was conducted to generate a mineral predictive map. Several image transformation and enhancement techniques were performed to Landsat Operational Land Imager (OLI) and Shuttle Radar Topography Mission (SRTM) data. Using band ratios and oriented principal component analysis (PCA) on OLI data allowed delineating hydrothermal alteration zones (HAZs) and highlighted structural discontinuity. Moreover, processing of the AMG using Standard Euler deconvolution and residual magnetic anomalies successfully revealed the subsurface structural features. Zones of hydrothermal alteration and surface/subsurface geologic structural density maps were combined through GIS technique. The results showed a mineral predictive map that ranked from very low to very high probability. Field validation allowed verifying the prepared map and revealed several mineralized sites including talc, talc-schist, gold mines and quartz veins associated with hematite. Overall, integration of RS and AMG data is a powerful technique in revealing areas of potential mineralization involved with hydrothermal processes.

Identify and diagnosis of homogenous units and separating them and eventually planning separately for each unit are considered the most principled way to manage units of forests and creating these trustable maps of forest’s types, plays important role in making optimum decisions for managing forest ecosystems in wide areas. Field method of circulation forest and Parcel explore to determine type of forest require to spend cost and much time. In recent years, providing these maps by using digital classification of remote sensing’s data has been noticed. The important tip to create these units is scale of map. To manage more accurate, it needs larger scale and more accurate maps. Purpose of this research is comparing observed classification of methods to recognize and determine type of forest by using data of Land Cover of Modis satellite with 1 kilometer resolution and on images of OLI sensor of LANDSAT satellite with 30 kilometers resolution by using vegetation indicators and also timely PCA and to create larger scale, better and more accurate resolution maps of homogenous units of forest. Eventually by using of verification, the best method was obtained to classify forest in Golestan province’s forest located on north-east of country.

Fire is one of the most serious hazards, which causes many economic, social, ecological, and human damages every year in the world. Fire in forests and natural ecosystems destroys wood, regeneration, forest vegetation, as well as soil erosion and forest regeneration problems (due to the dryness of the weather and the weakness of the soil). Awareness of the extent of the zones that have been fired is important for forest management. On the other hand, the difficulty of fieldwork due to the high cost and inaccessible roads, etc. reveals the need for using remote sensing science to solve this problem. In this research, MODIS satellite images were used to detect and determine the fire extent of Golestan province forests in northern Iran. MID13q1 and MOD13q1 images were used to detect the normal conditions of the environment. The 15-year time series data were provided for the NDVI and NDMI indicators in 2000-2015. Then, the behavior of indicators in the fire zone was studied on the day after the fire. The burned zones by the fire were specified by determining the appropriate threshold and then, they were compared to long-term normals. In the NDMI and NDVI indicators, the mean of the numeric value threshold limit for determining the burnt pixels was respectively 1.865 and 0.743 of the reduction in their normal long-term period, which are selected as fire pixels. The results showed that the NDMI index could determine the extent of the burned zone with the accuracy of 95.15%.

By reviewing US state-level panel data on infrastructure spending and on per capita income inequality from 1950 to 2010, this paper sets out to test whether an empirical link exists between infrastructure and inequality. Panel regressions with fixed effects show that an increase in the growth rate of spending on highways and higher education in a given decade correlates negatively with Gini indices at the end of the decade, thus suggesting a causal effect from growth in infrastructure spending to a reduction in inequality through better access to education and opportunities for employment. More significantly, this relationship is more pronounced with inequality at the bottom 40 percent of the income distribution. In addition, infrastructure expenditures on highways are shown to be more effective at reducing inequality. By carrying out a counterfactual experiment, the results show that those US states with a significantly higher bottom Gini coefficient in 2010 had underinvested in infrastructure during the previous decade. From a policy-making perspective, new innovations in finance for infrastructure investments are developed, for the US, other industrially advanced countries and also for developing economies.