A Tool for Classification and Regression Using Random Forest Methodology: Applications to Landslide Susceptibility Mapping and Soil Thickness Modeling

Classification and regression problems are a central issue in geosciences. In this paper, we present Classification and Regression Treebagger (ClaReT), a tool for classification and regression based on the random forest (RF) technique. ClaReT is developed in Matlab and has a simple graphic user interface (GUI) that simplifies the model implementation process, allows the standardization of the method, and makes the classification and regression process reproducible. This tool performs automatically the feature selection based on a quantitative criterion and allows testing a large number of explanatory variables. First, it ranks and displays the parameter importance; then, it selects the optimal configuration of explanatory variables; finally, it performs the classification or regression for an entire dataset. It can also provide an evaluation of the results in terms of misclassification error or root mean squared error. We tested the applicability of ClaReT in two case studies. In the first one, we used ClaReT in classification mode to identify the better subset of landslide conditioning variables (LCVs) and to obtain a landslide susceptibility map (LSM) of the Arno river basin (Italy). In the second case study, we used ClaReT in regression mode to produce a soil thickness map of the Terzona catchment, a small sub-basin of the Arno river basin. In both cases, we performed a validation of the results and a comparison with other state-of-the-art techniques. We found that ClaReT produced better results, with a more straightforward and easy application and could be used as a valuable tool to assess the importance of the variables involved in the modeling.     

Application of Adjoint Approach to Oil Spill Problems

Adjoint method is applied to various oil spill problems. A three-dimensional model for describing the dispersion of a quasi-passive substance (a pollutant or a nutrient) and its adjoint model are considered in a limited sea region. Direct and adjoint estimates are used to get dual (equivalent) estimates of the mean concentration of the substance in important zones of the region. The role of dual estimates is illustrated with a few examples. They include such oil spill problems as the search of the most dangerous point of the oil tanker route, the oil dispersion with a climatic velocity, and the dependence of the oil concentration estimates on the oil spill rate. One more example is the application of optimal bioremediation strategy for cleaning a few zones polluted by oil. In this case, instead of oil, the model describes the dispersion of a nutrient released to marine environment. Balanced, unconditionally stable second-order finite-difference schemes based on the splitting method for the solution of the dispersion model and its adjoint are suggested. The main and adjoint difference schemes are compatible in the sense that at every fractional step of the splitting algorithm, the one-dimensional split operators of both schemes satisfy a discrete form of Lagrange identity. In the special unforced and non-dissipative case, each scheme has two conservation laws. Every split one-dimensional problem is solved by Thomas’ factorization method.     

Marine Reserve Design with Ocean Currents and Multiple Objectives

There is a growing tendency to consider marine reserves as a management and conservation tool. We investigate a spatial bio-economic model to determine fishery profits under conservation efforts. Rather than imposing a marine reserve on our model, we ask, “When and where should a marine reserve be implemented ?” For one-dimensional habitat, we determine conditions under which marine reserves emerge as a part of the optimal policy. Depending upon the size of the habitat, the optimal strategy is either to avoid fishing or to fish at maximum rate. The effect of ocean currents is analyzed through numerical simulations. We find that in the presence of strong currents, a marine reserve may become ineffective. If the currents are at low rate, a marine reserve could emerge as a variable management tool.     

The Importance of Human Ecology at the Threshold of the Next Millennium: How Can Population Growth Be Stopped?

 Ecology is defined as the set of complex interactions between the biotic and abiotic environments. Human ecology concerns principally the population ecology "only" of Homo sapiens, but it also includes all aspects of global ecology because humans are the most important species. Human demography is characterized by a recent decline in mortality and fertility rates. These demographic transitions have largely been completed in industrialized countries, but not in the 140 developing countries. Approximately 100 countries are following the same demographic pattern as industrialized countries, however with a time delay of several generations. China has effectively reduced its population increase by means that would be unacceptable in Western democracies. Some 44 developing countries still show increasing population growth and no detectable demographic transition in birth rate. Thus one part of the world shows limited (and, in the long run, shrinking) population growth, and another continues with a strong increase. All populations are limited in their development by their sustainability by their environment, for example, food and energy resources, and the extent of pollution which the use of these resources produces. It is argued that in the case of human population the limits of sustainability have already been reached with the 6 billion humans alive today, since at least 20% of these suffer from hunger, natural resources are overexploited, and biodiversity is threatened. In the coming 200 years it is more likely that the total population will substantially oscillate rather than approach the predicted 12 billion. The most important goal of human ecology should therefore be to slow population growth as far as possible.     

A fetus with a parvovirus B19 infection and congenital anomalies

A fetus with multiple structural defects was seen at prenatal ultrasound examination. After termination of the pregnancy a bilateral cleft lip, alveolus, and palate; micrognathia; and webbed joints were seen. Fetal tissues showed indications of infection, intranuclear inclusion bodies, chronic stress, haemolysis, arterial wall damage, and profuse haemorrhage. Parvovirus B19 DNA was detected in fetal tissues by dot hybridization after polymerase chain reaction. The possibility of parvovirus B19 infection leading to congenital malformations is discussed.     

Human parvovirus B19 infection and unbalanced translocation in a case of hydrops fetalis

In a case of hydrops fetalis, serological examination showed a recent maternal human parvovirus B19 infection. Amniocentesis revealed a unique unbalanced translocation between chromosomes 3 and 11 of the fetus. The mother proved to have a balanced reciprocal translocation between chromosomes 3 and 11. A grossly macerated hydropic male fetus was delivered with a flat nose and low implanted deformed ears. Histopathological examination revealed nuclear inclusion bodies in fetal erythroid cells, confirming human parvovirus B19 infection. Parvovirus B19 DNA was demonstrated by in situ hybridization in the nuclei of heart muscle cells. Our finding of two different disorders in one case illustrates the importance of a complete evaluation of every case of hydrops fetalis, especially concerning counselling on the outcome of future pregnancies. The human parvovirus B19 infection will not recur due to the acquired immunity of the mother, whereas the balanced reciprocal translocation will endanger future pregnancies.     

Early amniocentesis—a cytogenetic evaluation of over 1500 cases

We report our cytogenetic experience of 1554 early amniocenteses between weeks 11 and 14 of gestation, of which 44 per cent were performed prior to week 14. The mean culture time was 14·5 days. Karyotyping was successful in 99·7 per cent of cases. In 9·9 per cent of cases, there was pseudomosaicism with a high rate of loss of an X-chromosome and structural aberration of chromosome 1, which may be due to the Chang medium. The mosaic rate was 0·5 per cent. The overall aberration rate was 2·8 per cent. Our data confirm the reliability of early amniocentesis, which is a serious alternative to standard amniocentesis and chorionic villus sampling (CVS).     

Maternal age-specific risks for trisomies at 9—14 weeks' gestation

This study provides data on the incidence of fetal trisomies 21, 18, and 13 at 9–14 weeks' gestation in women aged 35–45 years and estimates of maternal age-specific risks in women aged 20–45 years. Our data from 5814 singleton pregnancies undergoing first-trimester karyotyping for the sole indication of maternal age ⩾ 35 years were combined with those from two previous reports and the incidence of the trisomies was calculated from a total of 15 793 pregnancies. Comparison of incidences at 9–14 weeks' gestation with published data at 15–20 weeks' gestation and in livebirths demonstrated that at birth the maternal age-specific incidence of trisomy 21 is 33 per cent lower than at 15–20 weeks' gestation and 54 per cent lower than at 9–14 weeks' gestation. Furthermore, the relative frequency of trisomies 18 and 13 decreases from 30 per cent at 9–14 weeks to 22 per cent at 15–20 weeks and 14 per cent at birth.     

Pitfalls in the prenatal diagnosis of peroxisomal β-oxidation defects by chorionic villus sampling

Variability in the level of expression of very long chain fatty acids (VLCFAs) is documented in cultured chorionic villus (CV) cells derived from two fetuses, one at risk for an unusual peroxisomal fatty acid β-oxidation defect, and the other at risk for the X-linked form of adrenoleucodystrophy (ALD). Cells from early subcultures of chorionic cells from both cases gave normal values for VLCFA ratios. The results for the fetus at risk for the β-oxidation defect were interpreted to indicate that the fetus was not affected; however, at birth, the infant was clinically and biochemically affected. In the case of the fetus at risk for X-linked ALD, although VLCFAs were normal in subculture 1, the levels of these fatty acids increased dramatically in subculture 3, suggesting an abnormal fetus. Termination of the pregnancy and subsequent biochemical and morphological follow-up confirmed that the fetus was indeed affected by ALD.