Marco Painho

Self-organizing maps as substitutes for k-means clustering

One of the most widely used clustering techniques used in GISc problems is the k-means algorithm. One of the most important issues in the correct use of k-means is the initialization procedure that ultimately determines which part of the solution space will be searched. In this paper we briefly review different initialization procedures, and propose Kohonen’s Self-Organizing Maps as the most convenient method, given the proper training parameters. Furthermore, we show that in the final stages of its training procedure the Self-Organizing Map algorithms is rigorously the same as the k-means algorithm. Thus we propose the use of Self-Organizing Maps as possible substitutes for the more classical k-means clustering algorithms.

The self-organizing map, the Geo-SOM, and relevant variants for geosciences

In this paper we explore the advantages of using Self-Organized Maps (SOMs) when dealing with geo-referenced data. The standard SOM algorithm is presented, together with variants which are relevant in the context of the analysis of geo-referenced data. We present a new SOM architecture, the Geo-SOM, which was especially designed to take into account spatial dependency. The strengths and weaknesses of the different variants proposed are shown through a set of tests based on artificial data. A real world application of these techniques is given through the analysis of geodemographic data from Lisbons metropolitan area.

Applying genetic algorithms to zone design

Genetic algorithms (GA) have been found to provide global near optimal solutions in a wide range of complex problems. In this paper genetic algorithms have been used to deal with the complex problem of zone design. The zone design problem comprises a large number of geographical tasks, from which electoral districting is probably the most well known. The electoral districting problem is described and formalized mathematically. Different problem encodings, suited to GA optimization, are presented, together with different objective functions. A practical real world example is given and tests performed in order to evaluate the effectiveness of the GA approach.

Spatial sampling design for sediment quality assessment in estuaries

Abstract Unusual difficulties are encountered when characterizing the spatial distribution of the properties that collectively define the state of estuaries. Due to the variability of these estuarine conditions, greater sampling efforts are often necessary to describe estuarine environments, as compared to other aquatic systems. That is why in coastal management studies, where the collection of data is sometimes very difficult and time-consuming, a robust sampling strategy is essential. The aim of this study is to design a spatial sampling strategy for estuarine sediments, using prior information on the spatial variation of sediment granulometry. Systematic unaligned sampling with a grid cell size of 750×500 m was chosen on the basis of semi-variogram analysis, and was shown to have distinct advantages. This design was sampled for sediment parameters using a GPS-receiver and mapped within the digitized shoreline of the estuary. The estuary shoreline was digitized on the basis of aerial ortho-photography with tidal ebb determination. The sampling is intended to define the boundaries of environmental management areas for the Sado Estuary, situated on the west coast of Portugal. The research represents one of the initial phases in the development of a Sado Estuary environmental management system integrated into a Geographic Information System.

Ecological risk assessment of sediment management areas : application to Sado Estuary, Portugal

The purpose of this work was to integrate different methodologies to assess the potential ecological risk of estuarine sedimentary management areas, using the Sado Estuary in Portugal as case study. To evaluate the environmental risk of sediment contamination, an integrative and innovative approach was used involving assessment of sediment chemistry, sediment toxicity, benthic community structure, human driving forces and pressures and management areas organic load levels. The basis for decision-making for overall assessment was a statistical multivariate analysis appended into a score matrix tables, using a best expert judgment. The integrated approach allowed to identify from the 19 management areas analyzed, three with no risk but other three with high risk to cause adverse effects in the biota, related with the contaminants analyzed. The methodologies used showed to be effective as a support for decision making leading to future estuarine management recommendations.

Geo-Self-Organizing Map (Geo-SOM) for Building and Exploring Homogeneous Regions

Regionalization and uniform/homogeneous region building constitutes one of the most longstanding concerns of geographers. In this paper we explore the Geo-Self-Organizing Map (Geo-SOM) as a tool to develop homogeneous regions and perform geographic pattern detection. The Geo-SOM presents several advantages over other available methods. The possibility of “what-if” analysis, coupled with powerful visualization tools and the accommodation of spatial constraints, constitute some of the most relevant features of the Geo-SOM. In this paper we show the opportunities made available by this tool and explore different features which allow rich exploratory spatial data analysis.

Investigating the Potential of OpenStreetMap for Land Use/Land Cover Production: A Case Study for Continental Portugal

In the last decade, volunteers have been contributing massively to what we know nowadays as Volunteered Geographic Information (VGI). Through the research that has been conducted recently, it has become clear that this huge amount of information might hide interesting and rich geographical information. The OpenStreetMap (OSM) project is one of the most well-known and studied VGI initiatives. It has been studied to identify its potential for different applications. In the field of Land Use/Cover, an earlier study by the authors explored the use of OSM for Land Use/Cover (LULC) validation. Using the COoRdination of INformation on the Environment (CORINE) Land Cover (CLC) database as the Land Use reference data, they analyzed the OSM coverage and classification accuracy, finding an interesting global accuracy value of 76.7 % for level 1 land classes, for the study area of continental Portugal, despite a very small coverage value of approximately 3.27 %. In this chapter we review the existing literature on using OSM data for LULC database production and move this research forwards by exploring the suitability of the OSM Points of Interest dataset. We conclude that OSM can give very interesting contributions and that the OSM Points of Interest dataset is suitable for those classified as CLC class 1 which represents artificial surfaces.

Flickr Geotagged and Publicly Available Photos: Preliminary Study of Its Adequacy for Helping Quality Control of Corine Land Cover

Volunteered Geographic Information has become exponentially available over the Web in the last years. This availability can hide a vast geographical richness and provides us with both a great opportunity to explore new ways to use it and also big challenges related with its unstructured nature. In this paper we conduct a preliminary analysis of the adequacy of photos from the Flickr initiative in order to use them as a source of field data in the quality control of the Land Use/Cover databases production. We evaluate its temporal and spatial distributions over Continental Portugal and also its distribution over Land Use/Cover classes using as a reference the European Corine Land Cover database. We conclude that this source is very valuable but needs to be combined with other sources due to some issues related with its spatial distribution.

Crop Monitoring Based on SPOT-5 Take-5 and Sentinel-1A Data for the Estimation of Crop Water Requirements

Optical and microwave images have been combined for land cover monitoring in different agriculture scenarios, providing useful information on qualitative and quantitative land cover changes. This study aims to assess the complementarity and interoperability of optical (SPOT-5 Take-5) and synthetic aperture radar (SAR) (Sentinel-1A) data for crop parameter (basal crop coefficient (Kcb) values and the length of the crop’s development stages) retrieval and crop type classification, with a focus on crop water requirements, for an irrigation perimeter in Angola. SPOT-5 Take-5 images are used as a proxy of Sentinel-2 data to evaluate the potential of their enhanced temporal resolution for agricultural applications. In situ data are also used to complement the Earth Observation (EO) data. The Normalized Difference Vegetation Index (NDVI) and dual (VV + VH) polarization backscattering time series are used to compute the Kcb curve for four crop types (maize, soybean, bean and pasture) and to estimate the length of each phenological growth stage. The Kcb values are then used to compute the crop’s evapotranspiration and to subsequently estimate the crop irrigation requirements based on a soil water balance model. A significant R2 correlation between NDVI and backscatter time series was observed for all crops, demonstrating that optical data can be replaced by microwave data in the presence of cloud cover. However, it was not possible to properly identify each stage of the crop cycle due to the lack of EO data for the complete growing season.

Linking Agricultural Policies with Decision-Making: A Spatial Approach

Abstract The loss of agricultural land and its implications have been of great concern in the last decade. By undertaking a spatial analysis of the appropriation of agricultural land for urban use with an overlay of population and urban data, a focus on the consequences of certain regulations on the dynamics of land-use change is explored. This is achieved by integration of data inventories of agricultural land use for Portugal, and linking this information with CORINE Land Cover data as to assess change in the Algarve. An integrated assessment of agricultural land loss follows, undermined by the consequences of urban sprawl. In this sense, this paper expands on the currently existing decrees which provide support to sustainable development in the region while providing a qualitative assessment of future roles based on ethical values and economic efficiency and offering a feasible framework for policy-makers regarding the trends of urban/agricultural dichotomy in a planning and decision-making context.