Textural classification of land cover using support vector machines: an empirical comparison with parametric, non parametric and hybrid classifiers in the Bolivian Amazon

Land cover classification is a key research field in remote sensing and land change science as thematic maps derived from remotely sensed data have become the basis for analyzing many socio-ecological issues. However, land cover classification remains a difficult task and it is especially challenging in heterogeneous tropical landscapes where nonetheless such maps are of great importance. The present study aims to establish an efficient classification approach to accurately map all broad land cover classes in a large, heterogeneous tropical area of Bolivia, as a basis for further studies (e.g., land cover-land use change). Specifically, we compare the performance of parametric (maximum likelihood), non-parametric (k-nearest neighbour and four different support vector machines - SVM), and hybrid classifiers, using both hard and soft (fuzzy) accuracy assessments. In addition, we test whether the inclusion of a textural index (homogeneity) in the classifications improves their performance. We classified Landsat imagery for two dates corresponding to dry and wet seasons and found that non-parametric, and particularly SVM classifiers, outperformed both parametric and hybrid classifiers. We also found that the use of the homogeneity index along with reflectance bands significantly increased the overall accuracy of all the classifications, but particularly of SVM algorithms. We observed that improvements in producer’s and user’s accuracies through the inclusion of the homogeneity index were different depending on land cover classes. Earlygrowth/degraded forests, pastures, grasslands and savanna were the classes most improved, especially with the SVM radial basis function and SVM sigmoid classifiers, though with both classifiers all land cover classes were mapped with producer’s and user’s accuracies of around 90%. Our approach seems very well suited to accurately map land cover in tropical regions, thus having the potential to contribute to conservation initiatives, climate change mitigation schemes such as REDD+, and rural development policies.

Differential growth responses to water balance of coexisting deciduous tree species are linked to wood density in a Bolivian tropical dry forest

A seasonal period of water deficit characterizes tropical dry forests (TDFs). There, sympatric tree species exhibit a diversity of growth rates, functional traits, and responses to drought, suggesting that each species may possess different strategies to grow under different conditions of water availability. The evaluation of the long-term growth responses to changes in the soil water balance should provide an understanding of how and when coexisting tree species respond to water deficit in TDFs. Furthermore, such differential growth responses may be linked to functional traits related to water storage and conductance. We used dendrochronology and climate data to retrospectively assess how the radial growth of seven coexisting deciduous tree species responded to the seasonal soil water balance in a Bolivian TDF. Linear mixed-effects models were used to quantify the relationships between basal area increment and seasonal water balance. We related these relationships with wood density and sapwood production to assess if they affect the growth responses to climate. The growth of all species responded positively to water balance during the wet season, but such responses differed among species as a function of their wood density. For instance, species with a strong growth response to water availability averaged a low wood density which may facilitate the storage of water in the stem. By contrast, species with very dense wood were those whose growth was less sensitive to water availability. Coexisting tree species thus show differential growth responses to changes in soil water balance during the wet season. Our findings also provide a link between wood density, a trait related to the ability of trees to store water in the stem, and wood formation in response to water availability.

Classificació i importància dels elements paisatgístics del territori Tsimane' segons la percepció local

En aquesta tesis es presenten els resultats de la investigació duta a terme a les comunitats indígenes Tsimane’ de l’Amazònia boliviana. La investigació estudia la percepció dels indígenes sobre l’etnoclassificació del seu territori. S’estableix una clau de classificació i es determina la importància dels elements paisatgístics del territori Tsimane’ segons la percepció local. Aquesta informació permetrà integrar el coneixement local dins dels programes de desenvolupament integral i de planificació territorial en l’Amazònia Boliviana. L’estudi conclou que la població Tsimane’ classifica els elements paisatgístics del seu entorn en 89 taques conformades per una espècies arbòria dominant i que estan incloses en un o més dels nou paisatges identificats: Därsi Därä, Sajras, Sinues Ojñi’, Mayes, Múcúya, Tsäquis Därä, Cum, Tajñi’ i Jaman. A partir d’un anàlisi multicriteri s’ha determinat una importància total per cada paisatge segons els següents criteris d’importància: diversitat de taques, activitats econòmiques realitzables, presència espiritual, percepció individual i importància relativa segons els altres paisatges. Així doncs s’ha trobat que el paisatge més important és el Därsi Därä (bosc primari caracteritzat per un estrat arbori superior a 50 metres d’altura). També s’han analitzat les dades discernint segons el gènere de l’entrevistat i segons la proximitat de les comunitats estudiades a la ciutat més propera.

Chagas Disease among the Latin American Adult population attending in a primary care center in Barcelona, Spain

Background/Aims: The epidemiology of Chagas disease, until recently confined to areas of continental Latin America, has undergone considerable changes in recent decades due to migration to other parts of the world, including Spain. We studied the prevalence of Chagas disease in Latin American patients treated at a health center in Barcelona and evaluated its clinical phase. We make some recommendations for screening for the disease. Methodology/Principal Findings: We performed an observational, cross-sectional prevalence study by means of an immunochromatographic test screening of all continental Latin American patients over the age of 14 years visiting the health centre from October 2007 to October 2009. The diagnosis was confirmed by serological methods: conventional in-house ELISA (cELISA), a commercial kit (rELISA) and ELISA using T cruzi lysate (Ortho-Clinical Diagnostics) (oELISA). Of 766 patients studied, 22 were diagnosed with T. cruzi infection, showing a prevalence of 2.87% (95% CI, 1.6-4.12%). Of the infected patients, 45.45% men and 54.55% women, 21 were from Bolivia, showing a prevalence in the Bolivian subgroup (n = 127) of 16.53% (95% CI, 9.6-23.39%). All the infected patients were in a chronic phase of Chagas disease: 81% with the indeterminate form, 9.5% with the cardiac form and 9.5% with the cardiodigestive form. All patients infected with T. cruzi had heard of Chagas disease in their country of origin, 82% knew someone affected, and 77% had a significant history of living in adobe houses in rural areas. Conclusions: We found a high prevalence of T. cruzi infection in immigrants from Bolivia. Detection of T. cruzi¿infected persons by screening programs in non-endemic countries would control non-vectorial transmission and would benefit the persons affected, public health and national health systems.