Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.

Machine learning for spatial environmental data. Theory, applications and software

The book presents the state of the art in machine learning algorithms (artificial neural networks of different architectures, support vector machines, etc.) as applied to the classification and mapping of spatially distributed environmental data. Basic geostatistical algorithms are presented as well. New trends in machine learning and their application to spatial data are given, and real case studies based on environmental and pollution data are carried out. The book provides a CD-ROM with the Machine Learning Office software, including sample sets of data, that will allow both students and researchers to put the concepts rapidly to practice.

The behavioral relevance of multisensory neural response interactions.

Sensory information can interact to impact perception and behavior. Foods are appreciated according to their appearance, smell, taste and texture. Athletes and dancers combine visual, auditory, and somatosensory information to coordinate their movements. Under laboratory settings, detection and discrimination are likewise facilitated by multisensory signals. Research over the past several decades has shown that the requisite anatomy exists to support interactions between sensory systems in regions canonically designated as exclusively unisensory in their function and, more recently, that neural response interactions occur within these same regions, including even primary cortices and thalamic nuclei, at early post-stimulus latencies. Here, we review evidence concerning direct links between early, low-level neural response interactions and behavioral measures of multisensory integration.

Mineralogical alteration of artificial meteorites during atmospheric entry. The STONE-5 experiment

The generic concept of the artificial meteorite experiment STONE is to fix rock samples bearing microorganisms on the heat shield of a recoverable space capsule and to study their modifications during atmospheric re-entry. The STONE-5 experiment was performed mainly to answer astrobiological questions. The rock samples mounted on the heat shield were used (i) as a carrier for microorganisms and (ii) as internal control to verify whether physical conditions during atmospheric re-entry were comparable to those experienced by "real" meteorites. Samples of dolerite (an igneous rock), sandstone (a sedimentary rock), and gneiss impactite from Haughton Crater carrying endolithic cyanobacteria were fixed to the heat shield of the unmanned recoverable capsule FOTON-M2. Holes drilled on the back side of each rock sample were loaded with bacterial and fungal spores and with dried vegetative cryptoendoliths. The front of the gneissic sample was also soaked with cryptoendoliths. <p>The mineralogical differences between pre- and post-flight samples are detailed. Despite intense ablation resulting in deeply eroded samples, all rocks in part survived atmospheric re-entry. Temperatures attained during re-entry were high enough to melt dolerite, silica, and the gneiss impactite sample. The formation of fusion crusts in STONE-5 was a real novelty and strengthens the link with real meteorites. The exposed part of the dolerite is covered by a fusion crust consisting of silicate glass formed from the rock sample with an admixture of holder material (silica). Compositionally, the fusion crust varies from silica-rich areas (undissolved silica fibres of the holder material) to areas whose composition is "basaltic". Likewise, the fusion crust on the exposed gneiss surface was formed from gneiss with an admixture of holder material. The corresponding composition of the fusion crust varies from silica-rich areas to areas with "gneiss" composition (main component potassium-rich feldspar). The sandstone sample was retrieved intact and did not develop a fusion crust. Thermal decomposition of the calcite matrix followed by disintegration and liberation of the silicate grains prevented the formation of a melt.</p> <p>Furthermore, the non-exposed surface of all samples experienced strong thermal alterations. Hot gases released during ablation pervaded the empty space between sample and sample holder leading to intense local heating. The intense heating below the protective sample holder led to surface melting of the dolerite rock and to the formation of calcium-silicate rims on quartz grains in the sandstone sample. (c) 2008 Elsevier Ltd. All rights reserved.</p>

Implicit methods for qualitative modeling of gene regulatory networks.

Advancements in high-throughput technologies to measure increasingly complex biological phenomena at the genomic level are rapidly changing the face of biological research from the single-gene single-protein experimental approach to studying the behavior of a gene in the context of the entire genome (and proteome). This shift in research methodologies has resulted in a new field of network biology that deals with modeling cellular behavior in terms of network structures such as signaling pathways and gene regulatory networks. In these networks, different biological entities such as genes, proteins, and metabolites interact with each other, giving rise to a dynamical system. Even though there exists a mature field of dynamical systems theory to model such network structures, some technical challenges are unique to biology such as the inability to measure precise kinetic information on gene-gene or gene-protein interactions and the need to model increasingly large networks comprising thousands of nodes. These challenges have renewed interest in developing new computational techniques for modeling complex biological systems. This chapter presents a modeling framework based on Boolean algebra and finite-state machines that are reminiscent of the approach used for digital circuit synthesis and simulation in the field of very-large-scale integration (VLSI). The proposed formalism enables a common mathematical framework to develop computational techniques for modeling different aspects of the regulatory networks such as steady-state behavior, stochasticity, and gene perturbation experiments.

Overcoming limitations of modelling rare species by using ensembles of small models

1. Species distribution models (SDMs) have become a standard tool in ecology and applied conservation biology. Modelling rare and threatened species is particularly important for conservation purposes. However, modelling rare species is difficult because the combination of few occurrences and many predictor variables easily leads to model overfitting. A new strategy using ensembles of small models was recently developed in an attempt to overcome this limitation of rare species modelling and has been tested successfully for only a single species so far. Here, we aim to test the approach more comprehensively on a large number of species including a transferability assessment. 2. For each species numerous small (here bivariate) models were calibrated, evaluated and averaged to an ensemble weighted by AUC scores. These 'ensembles of small models' (ESMs) were compared to standard Species Distribution Models (SDMs) using three commonly used modelling techniques (GLM, GBM, Maxent) and their ensemble prediction. We tested 107 rare and under-sampled plant species of conservation concern in Switzerland. 3. We show that ESMs performed significantly better than standard SDMs. The rarer the species, the more pronounced the effects were. ESMs were also superior to standard SDMs and their ensemble when they were independently evaluated using a transferability assessment. 4. By averaging simple small models to an ensemble, ESMs avoid overfitting without losing explanatory power through reducing the number of predictor variables. They further improve the reliability of species distribution models, especially for rare species, and thus help to overcome limitations of modelling rare species.