An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing

New Earth observation missions and technologies are delivering large amounts of data. Processing this data requires developing and evaluating novel dimensionality reduction approaches to identify the most informative features for classification and regression tasks. Here we present an exhaustive evaluation of Guided Regularized Random Forest (GRRF), a feature selection method based on Random Forest. GRRF does not require fixing a priori the number of features to be selected or setting a threshold of the feature importance. Moreover, the use of regularization ensures that features selected by GRRF are non-redundant and representative. Our experiments based on various kinds of remote sensing images, show that GRRF selected features provides similar results to those obtained when using all the available features. However, the comparison between GRRF and standard random forest features shows substantial differences: in classification, the mean overall accuracy increases by almost 6% and, in regression, the decrease in RMSE almost reaches 2%. These results demonstrate the potential of GRRF for remote sensing image classification and regression. Especially in the context of increasingly large geodatabases that challenge the application of traditional methods.     

Impact of land use covers upon karst processes in a typical Fengcong depression system of Nongla, Guangxi, China

The direction and intensity of karst processes can be deeply affected by soil physical and chemical variations which were resulted from land use. Taking Nongla Fengcong depression area, Mashan County, Guangxi as an example, authors discussed the impact of land use on karst processes based on the data of field limestone tablet. The results showed that the corrosional rates at varied soil depth are quite different. Corrosional rate in woodland and orchard is mostly bigger than 20 mg/a, which is much higher than that in tilled land and shrub. Generally, corrosional rate decreased from orchard, woodland, tilled land, fallow land and shrub successively, in which soil organic matter (OM) and soil pH are two major controlling factors: corrosion process is controlled remarkably by soil OM in woodland and orchard. The higher the organic matter content is and the less the pH value is, the higher the corrosional rate is. Owing to lower organic matter content, the corrosional rate is mainly affected by soil CO₂ in tilled land and shrub.     

Suitability analysis for sand and gravel extraction site location in the context of a sustainable development in the surroundings of Zaragoza (Spain)

Zaragoza city is located in the central Ebro Basin, in the Iberian Peninsula. The fluvial terraces formed by the Ebro River present a valuable resource of sand and gravel deposits. However, taking advantage of these available resources implies conflicts with other land use interests like urban and industrial development as well as agricultural use, which has also traditionally occupied the alluvial terraces. These deposits represent a substantial groundwater resource that should be preserved for future generations. The development of spatial decision support systems (SDSS) has greatly assisted efforts for solving land-use conflicts. These systems combine the benefits of geographic information systems (GIS) and decision support methodologies and are therefore suitable to manage sustainable development of urban areas. In this contribution, an extraction suitability map taking into consideration a variety of environmental criteria is created with the help of a SDSS. The method used is the analytical hierarchy process which is integrated in ArcGIS. Areas most suitable to sand and gravel extraction are located in the high terraces, and in those terraces covered by pediments where the thickness of resource is relatively high. These areas are far from valuable natural areas, outside areas most vulnerable to groundwater contamination, and beneath soils with poor irrigation characteristics.     

A modified DRASTIC model for Siting Confined Animal Feeding Operations in Williams County,Ohio, USA

Three of DRASTIC’s parameters (Depth to Water, Soil Media, and Topography) were modified and another parameter was added (land use/land cover) to the model to determine the potential impact on groundwater from Confined Animal Feeding Operations (CAFO) manure lagoon settings and manure application as fertilizer. Williams County is a mostly agricultural county located in northwest Ohio, USA. It currently has three CAFOs, all dairy, with the possibility of the construction of a multi-million chicken egg CAFO in the near future. A Geographic Information System (GIS) was utilized to modify the Ohio Department of Natural Resources (ODNR) DRASTIC map for the county to fully assess the county-wide pollution potential of CAFOs. The CAFO DRASTIC map indicates that almost half of Williams County has elevated groundwater pollution potential. The rest of the county, primarily the southeast corner, has lower CAFO groundwater pollution potential. Future CAFO development within the county should focus on the southeastern portion of the county where the groundwater table is deeper, and the aquifer is composed of shale substrate with low hydraulic conductivity. The CAFO DRASTIC results are intended to be used as a screening tool and are not to replace site-specific hydrogeologic investigations.     

Integrating diverse methods to understand climate-land interactions in East Africa

The questions of how land use change affects climate, and how climate change affects land use, require examination of societal and environmental systems across space at multiple scales, from the global climate to regional vegetative dynamics to local decision making by farmers and herders. It also requires an analysis of causal linkages and feedback loops between systems. These questions and the conceptual approach of the research design of the Climate-Land Interaction Project (CLIP) are rooted in the classical human-environment research tradition in Geography.This paper discusses a methodological framework to quantify the two-way interactions between land use and regional climate systems, using ongoing work by a team of multi-disciplinary scientists examining climate-land dynamics at multiple scales in East Africa. East Africa is a region that is undergoing rapid land use change, where changes in climate would have serious consequences for people’s livelihoods, and requiring new coping and land use strategies. The research involves exploration of linkages between two important foci of global change research, namely, land use/land cover (LULC) and climate change. These linkages are examined through modeling agricultural systems, land use driving forces and patterns, the physical properties of land cover, and the regional climate. Both qualitative and quantitative methods are being used to illustrate a diverse pluralism in scientific discovery.     

Tidal inundation mapping under enhanced land subsidence in Semarang,Central Java Indonesia

Tidal inundation by high tide under enhanced land subsidence is a damaging phenomenon and a major threat to the Semarang urban area in Indonesia. It impacts on economic activities, as well as the cost of an emergency program and causes interruption of pubic services, danger of infectious diseases and injury to human lives. This study examines a spatial analysis tool on the GIS-raster system for the tidal inundation mapping based on the subsidence-benchmark data and modified detail digital elevation model. Neighborhood operation and iteration model as a spatial analysis tool have been applied in order to calculate the encroachment of the tidal inundation on the coastal area. The resulting map shows that the tidal flood spreads to the lowland area and causes the inundation of coastal settlement, infrastructure, as well as productive agricultural land, i.e., the fish-pond area. The monitoring of the vulnerable area due to the tidal inundation under the scenario of extended land subsidence plays an important role in long-term coastal zone management in Semarang.     

The state of land subsidence and prediction approaches due to groundwater withdrawal in China

This article gives a general introduction to land subsidence with the prediction approaches due to withdrawal of groundwater in three subsided/subsiding regions in China: the deltaic plain of Yangtse River (YRDP), North China Plain (NCP), and Fenwei Plain (FP). On YRDP, Shanghai is the typical subsided/subsiding city; on NCP Tianjin is the typical subsided/subsiding city, and on FP Taiyuan is the typical subsided/subsiding city. The subsided area with subsidence over 200 mm on YRDP is about 10,000 km² and the maximum subsided value reached 2.9 m at Shanghai; on NCP the subsided area reached 60,000 km² with the maximum subsidence of 3.9 m at Tianjing; on FP the subsided area is relatively smaller than that on the other two plains and is about 1,135 km² with maximum subsidence of 3.7 m at Taiyuan city. In order to protect the civil and industrial facilities, it is necessary to predict the future development of land subsidence based on present state. Many researchers proposed several approaches to predict the land subsidence due to groundwater withdrawal according to different geological conditions and groundwater withdrawal practice. This article classifies these approaches into five categories: (i) statistical methods; (ii) 1D numerical method; (iii) quasi-3D seepage model; (iv) 3D seepage model; (v) fully coupled 3D model. In China, the former four categories are presently employed in the prediction practice and their merits and demerits are discussed. According to the prediction practice, 3D seepage model is the best method presently.     

Background concentrations of elements in surface soils and their changes as affected by agriculture use in the desert-oasis ecotone in the middle of Heihe River Basin,North-west China

The concentrations of twenty four chemical elements in the surface layer of natural desert soils and the cultivated farmland soils were measured at a desert-oasis ecotone in the middle of Heihe river basin, north-west China. Background values were estimated for (a) major elements (Si 335.3 g kg^− 1, Al 49.4 g kg^− 1, Fe 19.1 g kg^− 1, Ca 29.4 g kg^− 1, Mg 8.9 g kg^− 1, K 20.1 g kg^− 1, Na 17.5 g kg^− 1 and P 0.338 g kg^− 1), (b) heavy metals and non-metals (Cr 55.8 mg kg^− 1, Mn 404.8 mg kg^− 1, Ni 17.7 mg kg^− 1, Cu 5.1 mg kg^− 1, Zn 33.7 mg kg^− 1, Pb 15.5 mg kg^− 1 and As 5.2 mg kg^− 1) and (c) other trace elements (Ti 2.0 mg kg^− 1, V 55.3 mg kg^− 1, Co 5.7 mg kg^− 1, Rb 82.4 mg kg^− 1, Sr 232.9 mg kg^− 1, Y 14.7 mg kg^− 1, Zr 194.9 mg kg^− 1, Nb 7.8 mg kg^− 1 and Ba 720.6 mg kg^− 1). After natural desert soil was cultivated for agricultural use, significant changes in element concentrations occurred under tillage, irrigation and fertilisation management. Compared to natural soil, the for the levels of Si, K, Na, Sr, Zr and Ba decreased, and no changes were observed for Rb, while the values of the other 17 elements increase in agricultural soil from 1.2 to 3.5 times. However, their absolute concentrations are still low, suggesting that the arable soil in this region remains comparatively a clean soil. The increased silt, clay and organic carbon content, under long-term irrigation, enriched the fine-grained materials, and application of fertilisers and manure contributed to the accumulation of most elements in arable soil. The accumulation of elements in agricultural soil increased with increasing cultivation years and extent of soil development.     

Pervasive wetland flooding in the glacial drift prairie of North Dakota (USA)

This article describes a unique flood hazard, produced by the dramatic expansion of wetlands in Nelson County, located within the North American Prairie Pothole Region of North Dakota, USA. There has been an unprecedented increase in the number, average size, and permanence of prairie wetlands, and a significant increase in the size of a closed lake (Stump Lake) due to a decade-long wet spell that began in 1993 following a prolonged drying trend. Base-line land cover information from the 1992 USGS National Land Cover Characterization dataset, and a Landsat TM scene acquired 9 July 2001 are used to assess the growth of the closed lake and wetland pond surface areas, and to analyze the type and area of various land cover classes inundated between 1992 and 2001. The open water profile in Nelson County changed from one marked by relatively comparable coverage of closed lake and wetland pond areas in 1992, to one in which wetland open water accounted for the vast majority of total open water in 2001. The bulk of the wetland pond area expansion occurred by displacing existing wetland vegetation and agricultural cropland. Producers responded to the flood hazard by filing Federal Crop Insurance Corporation (FCIC) claims and enrolling cropland in the Conservation Reserve Program (CRP), a federal land retirement program. Land taken out of agricultural production has had an enormous impact upon the agricultural sector that forms the economic base of the rural economy. In 2001 the land taken out of production due to CRP enrollment and preventive planting claims represented nearly 42% of Nelson County’s 205.2 K ha base agricultural land. The patterns obtained from this detailed study of Nelson County are likely to be the representative of the more publicized flood disaster occurring within the Devils Lake Basin of North Dakota.