Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.

Correlation of male genital filaments and female spermathecal ducts in New World sand flies of the Lutzomyia intermedia species complex (Diptera: Psychodidae, Phlebotominae)

The lengths of the male genital filaments and female spermathecal ducts were measured in phlebotomine sand flies of the Lutzomyia intermedia species complex and the ratios between these characters calculated. Ratios for L. intermedia s. s. from Northeast vs Southeast Brazil (Espírito Santo and Minas Gerais), Espírito Santo/Minas Gerais vs Rio de Janeiro/São Paulo and L. intermedia vs L. neivai were significantly different at P < 0.1, 0.05 and 0.01 respectively when compared using ANOVA. The spermathecal ducts and genital filaments of L. intermedia were significantly longer than those of L. neivai (P < 0.01) and could be used to differentiate these species. The taxonomic and biological significance of these differences is discussed.

Involvement of environmental mercury and lead in the etiology of neurodegenerative diseases.

The incidence of neurodegenerative disease like Parkinson's disease and Alzheimer's disease (AD) increases dramatically with age; only a small percentage is directly related to familial forms. The etiology of the most abundant, sporadic forms is complex and multifactorial, involving both genetic and environmental factors. Several environmental pollutants have been associated with neurodegenerative disorders. The present article focuses on results obtained in experimental neurotoxicology studies that indicate a potential pathogenic role of lead and mercury in the development of neurodegenerative diseases. Both heavy metals have been shown to interfere with a multitude of intracellular targets, thereby contributing to several pathogenic processes typical of neurodegenerative disorders, including mitochondrial dysfunction, oxidative stress, deregulation of protein turnover, and brain inflammation. Exposure to heavy metals early in development can precondition the brain for developing a neurodegenerative disease later in life. Alternatively, heavy metals can exert their adverse effects through acute neurotoxicity or through slow accumulation during prolonged periods of life. The pro-oxidant effects of heavy metals can exacerbate the age-related increase in oxidative stress that is related to the decline of the antioxidant defense systems. Brain inflammatory reactions also generate oxidative stress. Chronic inflammation can contribute to the formation of the senile plaques that are typical for AD. In accord with this view, nonsteroidal anti-inflammatory drugs and antioxidants suppress early pathogenic processes leading to Alzheimer's disease, thus decreasing the risk of developing the disease. The effects of lead and mercury were also tested in aggregating brain-cell cultures of fetal rat telencephalon, a three-dimensional brain-cell culture system. The continuous application for 10 to 50 days of non-cytotoxic concentrations of heavy metals resulted in their accumulation in brain cells and the occurrence of delayed toxic effects. When applied at non-toxic concentrations, methylmercury, the most common environmental form of mercury, becomes neurotoxic under pro-oxidant conditions. Furthermore, lead and mercury induce glial cell reactivity, a hallmark of brain inflammation. Both mercury and lead increase the expression of the amyloid precursor protein; mercury also stimulates the formation of insoluble beta-amyloid, which plays a crucial role in the pathogenesis of AD and causes oxidative stress and neurotoxicity in vitro. Taken together, a considerable body of evidence suggests that the heavy metals lead and mercury contribute to the etiology of neurodegenerative diseases and emphasizes the importance of taking preventive measures in this regard.

Population dynamics of intermediate snail hosts of Fasciola hepatica and some environmental factors in San Juan y Martinez municipality, Cuba

The variation of abundances of intermediate snail hosts of Fasciola hepatica in Cuba (Fossaria cubensis and Pseudosuccinea columella) was studied during one year under natural conditions at five sampling sites in San Juan y Martinez municipality, Pinar del Rio province, Cuba. The effect of some environmental variables on the lymnaeid abundances was also studied. A canonical correspondence analysis showed that both species do not generally occur together in the same habitat and that most factors affect them in an opposite fashion, although both of them correlate positively through time to the diversity of the habitats. F. cubensis prefers the sites that are in or closer to the city whereas P. columella is more abundant in rural sites. Lymnaeid abundances are mainly affected by nitrite and nitrate concentrations as well as by the abundance of the thiarid Tarebia granifera. F. cubensis is more abundant in polluted habitats with low densities (or absence) of T. granifera whereas P. columella prefers cleaner habitats and can coexist with the thiarid, even at its higher densities. The implications of divergent preferences of the two lymnaeids for the control of fasciolosis are discussed.

Distribution and Schistosoma mansoni infection of Biomphalaria glabrata in different habitats in a rural area in the Jequitinhonha Valley, Minas Gerais, Brazil: environmental and epidemiological aspects

This paper examines the distribution and infection of Biomphalaria glabrata with Schistosoma mansoni in all aquatic snail habitats in a rural area in the state of Minas Gerais, Brazil, in relation to physico/biotic and behavioral factors. Snail and environmental surveys were carried out semi-annually between July 2001 and November 2002 at 106 sites. Collected snails were examined in the laboratory for infection. B. glabrata densities were highest in overflow ponds, irrigation ponds, springs, canals and wells, and lowest in fishponds and water tanks. Snail densities were higher during the hot, rainy season except for streams and canals and were statistically associated with the presence of fish, pollution, and vegetation density. Tilapia fish and an unidentified Diptera larva were found to be predators of B. glabrata but ducks were not. Twenty-four of the 25 infected snails were collected in 2001(1.4% infection rate) and only one in 2002, after mass chemotherapy. The occurrence of B. glabrata in all 11 snail habitats both at and away from water contact sites studied indicates widespread risk of human infection in the study area. In spite of the strong association between B. glabrata and tilapia in fishponds we do not recommend its use in schistosomiasis control for ecological reasons and its relative inefficiency in streams and dams.

Factors associated with schistosomiasis mansoni in a population from the municipality of Jaboticatubas, State of Minas Gerais, Brazil

Jaboticatubas is a municipality in the metropolitan region of Belo Horizonte which has been a target of a wide media release as "the capital of schistosomiasis" since the 1960's. In order to give support to a work based on an integrated control, we sought to identify the disease determinants at the site. A transversal study was carried out aimed at identifying prevalence rates of the disease and factors associated with the infection in the district of São José de Almeida, and two close localities, Cipó Velho and São José da Serra, all of them located in the municipality of Jaboticatubas. A parasitological survey was performed, applying the Kato-Katz method with two slides per sample in 1186 schoolchildren which represents 77% of all registered pupils in four public schools in 2001. Among these schoolchildren a number of 101 (8.6%) prooved positive for Schistosoma mansoni eggs in their stool samples. A total of 64 families, whose schoolchildren had shown to be positive for schistosomiasis, also undertook examinations. As negative control, a random sample was collected from the 206 families, whose children had proven negative for schistosomiasis. The prevalence among 270 families (1304 people) was 12%. To assess those who continued to have contact with possibly contaminated water, 1061 (81.4%) people of the 270 families were interviewed. A multivariate analysis identified the following factors associated with the infection: time of residence in the area (short period), garbage disposal (use of deserted areas), gender (male), age (from 10 to 29 years), and water contact (daily and weekly). Further analysis of these factors revealed a close correlation between water contact and the disease, with a positive significant frequency concerning almost all those items. Depending on gender and age significant variations of water contact patterns associated with leisure and professional activities were found. A malacological survey on water collections in the area identified snails of the species Biomphalaria straminea and B. glabrata. The latter showed 17 (0.6%) specimens positive for S. mansoni. Qualitative studies have complemented such evidences, which allowed us to design a reference picture and specific indicators of the disease for the local population. Those data provided the essential information to continue the development of an already ongoing educative process, as well as projects on environmental improvements.

Habitat preference of freshwater snails in relation to environmental factors and the presence of the competitor snail Melanoides tuberculatus (Müller, 1774)

Our objective is to evaluate the habitat preference of freshwater snails in relation to environmental factors and the presence of the competitor snail Melanoides tuberculatus. In the first phase, snails was collected at 12 sites. This sampling sites presented a degree of organic input. In the second phase 33 sampling sites were chosen, covering a variety of lotic and lentic environments. The snail species found at Guapimirim, state of Rio de Janeiro, displayed a marked habitat preference, specially in relation to the physical characteristics of each environment. Other limiting factors for snail distribution at the studied lotic environments were the water current velocity and the amount of organic matter, mainly to Physa marmorata, M. tuberculatus, and Biomphalaria tenagophila. The absence of interactions between M. tuberculatus and another snails could be associated to the distinct spatial distribution of those species and the instability of habitats. This later factor may favor the coexistence of M. tuberculatus with B. glabrata by reduction of population density. In areas of schistosomiasis transmission some habitat modification may add to the instability of the environment, which would make room for the coexistence of M. tuberculatus and Biomphalaria spp. In this way, some of the usual measures for the control of snail hosts would prevent the extinction of populations of Biomphalaria spp. by M. tuberculatus in particular habitats.

Indoor air microbiological evaluation of offices, hospitals, industries, and shopping centers

In this study it was compared the MAS-100 and the Andersen air samplers' performances and a similar trend in both instruments was observed. It was also evaluated the microbial contamination levels in 3060 samples of offices, hospitals, industries, and shopping centers, in the period of 1998 to 2002, in Rio de Janeiro city. Considering each environment, 94.3 to 99.4% of the samples were the allowed limit in Brazil (750 CFU/m³). The industries' results showed more important similarity among fungi and total heterotrophs distributions, with the majority of the results between zero and 100 CFU/m³. The offices' results showed dispersion around 300 CFU/m³. The hospitals' results presented the same trend, with an average of 200 CFU/m³. Shopping centers' environments showed an average of 300 CFU/m³ for fungi, but presented a larger dispersion pattern for the total heterotrophs, with the highest average (1000 CFU/m³). It was also investigated the correlation of the sampling period with the number of airborne microorganisms and with the environmental parameters (temperature and air humidity) through the principal components analysis. All indoor air samples distributions were very similar. The temperature and air humidity had no significant influence on the samples dispersion patterns.

Burden of Disease: Environmental Inequalities

A report on Environmental Inequalities in the UK. Part of the Burden of disease. A clean and healthy environment is a vital component of public health. This is particularly so for children. They are more sensitive to most stressors during development and growth and receive relatively more exposure than adults due to behaviour patterns, lack of awareness, size and biological metabolisms.A study of the contribution of environmental pollutants to the incidence, prevalence, mortality and costs of four categories of paediatric disease in American children estimated total annual costs to be $54.9 billion comprising $43.4 billion for lead poisoning, $2.0 billion for asthma, $0.3 billion for childhood cancer, and $9.2 billion for neurobehavioral disorders; 2.8 % of total U.S. health care costs. As well as childhood conditions, some adult diseases, even those that emerge much later in life, e.g. hypertension, hyperlipidemia, insulin resistance, type 2 diabetes, ischemic heart disease, breast cancer and prostate cancer have some of their origins in utero and childhood. Childhood exposures to environmental health hazards may therefore constitute a source of inequity between generations .

Cleaning up neighbourhoods - Environmental Problems and Service Provision in Deprived areas

There has been growing concern that the quality of public services can be affected by the nature and scale of problems in deprived neighbourhoods and that poor services can contribute to a widening gap۪ between deprived and non-deprived neighbourhoods. There is also an increased emphasis within national policy on the quality of neighbourhood environments the so-called liveability۪ agenda. This report explores the challenges of delivering street scene۪ environmental services such as street sweeping and refuse collection in deprived and less deprived areas and examines the gap in environmental amenity between these different neighbourhoods. It also contributes to our understanding of the interplay between poor services and neighbourhood decline. The research involved a telephone survey of chief officers in local authority environmental service departments across the UK and detailed case studies of policy and practice in environmental service provision in four local authorities with significant levels of deprivation. Each case study involved work in three neighbourhoods within the authority two deprived and one less deprived as well as focus groups with residents and frontline environmental operatives, interviews with senior council staff and observation on the ground

Epidemiology of visceral leishmaniasis through spatial analysis, in Belo Horizonte municipality, state of Minas Gerais, Brazil

The geographic information system approach has permitted integration between demographic, socio-economic and environmental data, providing correlation between information from several data banks. In the current work, occurrence of human and canine visceral leishmaniases and insect vectors (Lutzomyia longipalpis) as well as biogeographic information related to 9 areas that comprise the city of Belo Horizonte, Brazil, between April 2001 and March 2002 were correlated and georeferenced. By using this technique it was possible to define concentration loci of canine leishmaniasis in the following regions: East; Northeast; Northwest; West; and Venda Nova. However, as for human leishmaniasis, it was not possible to perform the same analysis. Data analysis has also shown that 84.2% of the human leishmaniasis cases were related with canine leishmaniasis cases. Concerning biogeographic (altitude, area of vegetation influence, hydrographic, and areas of poverty) analysis, only altitude showed to influence emergence of leishmaniasis cases. A number of 4673 canine leishmaniasis cases and 64 human leishmaniasis cases were georeferenced, of which 67.5 and 71.9%, respectively, were living between 780 and 880 m above the sea level. At these same altitudes, a large number of phlebotomine sand flies were collected. Therefore, we suggest control measures for leishmaniasis in the city of Belo Horizonte, giving priority to canine leishmaniasis foci and regions at altitudes between 780 and 880 m.