Patricio Perez

Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago, Chile

Hourly average concentrations of PM2.5 have been measured at a fixed point in the downtown area of Santiago, Chile. We have focused our attention on data for the months that register higher values, from May to September, on years 1994 and 1995. We show that it is possible to predict concentrations at any hour of the day, by fitting a function of the 24 hourly average concentrations measured on the previous day. We have compared the predictions produced by three different methods: multilayer neural networks, linear regression and persistence. Overall, the neural network gives the best results. Prediction errors go from 30% for early hours to 60% for late hours. In order to improve predictions, the effect of noise reduction, rearrangement of the data and explicit consideration of meteorological variables are discussed.

Prediction of NO and NO2 concentrations near a street with heavy traffic in Santiago, Chile

Abstract Based on NO concentrations and meteorological variables recorded hourly at a point close to an avenue with heavy traffic in the city of Santiago, we are able to build a simple model that allows prediction of NO concentrations several hours in advance. Predicted NO concentrations in conjunction with forecasted meteorological data may be used to predict NO2 concentrations with reasonable accuracy. We compare predictions generated using persistence, linear regressions and multi layer neural networks.

Prediction of Particlulate Air Pollution using Neural Techniques

We have analysed the possibility of predicting hourly average concentrations of suspended atmospheric particulate matter with aerodynamic diameter less than 2.5 microns (PM2.5) several hours in advance using data obtained in downtown Santiago, Chile. By performing some standard tests used in the study of dynamical systems, we are able to extract some features of the time series of data. We use this information to estimate the amount of data on the past to be used as input to a neural network in order to predict future values of PM2.5 concentrations. We show that improvement of predictions is possible by using another neural network for noise reduction on the original series. The best results are obtained with a type of neural network which is equivalent to a linear regression. Up to six hours in advance, predictions generated in this way have significantly smaller errors than predictions based on the persistence of the long term average of the data.

Statistical modelling and prediction of atmospheric pollution by particulate material: two nonparametric approaches

Atmospheric particles are one of the main factors of air pollution in Santiago, Chile. Inhalation of particulate material is known to lead to serious health problems, including respiratory illness and complications related thereto. Vehicular traffic, industrial activity and street dust are important sources of atmospheric particles. The public authorities in Santiago have been monitoring air pollution by means of a network of semi-automatic sampling stations. At one of these stations, located near the city centre close to Government House, both PM2.5 and PM10 particulate material concentrations have been measured continuously for several years. Here PM2.5 refers to particles having a diameter smaller than 2.5 microns and PM10 corresponds to particles smaller than 10 microns. Hourly averages of the concentrations are available. For the present work, hourly data recorded at intervals of 12 hours have been used. The aim is to describe and forecast these variables with satisfactory precision, including critical pollution episodes, both as a function of previous behaviour and of a set of meteorological variables, comprising wind speed and direction, ambient temperature and relative air humidity. Both non-parametric discriminant analysis and multivariate adaptive regression splines procedures have been applied. Highly satisfactory classification as well as forecasting results were achieved with these approaches, respectively. Copyright

Competing mechanisms for the transport of energy in the α-helix

Abstract The Davydov model for a molecular chain of hydrogen-bonded peptide groups admits lattice acoustic as well as intramolecular solitons when the anharmonicity of the H-bond is explicitly taken into account. On the basis of a numerical simulation we suggest that such (supersonic) lattice solitons may present a more efficient alternative than the original (subsonic) selftrapped Davydov soliton for transporting energies under realistic conditions.

Carbon monoxide concentration forecasting in Santiago, Chile.

Abstract In the city of Santiago, Chile, air quality is defined in terms of particulate matter with an aerodynamic diameter ≤10 μm (PM10) concentrations. An air quality forecasting model based on past concentrations of PM10 and meteorological conditions currently is used by the metropolitan agency for the environment, which allows restrictions to emissions to be imposed in advance. This model, however, fails to forecast between 40 and 50% of the days considered to be harmful for the inhabitants every year. Given that a high correlation between particulate matter and carbon monoxide (CO) concentrations is observed at monitoring stations in the city, a model for CO concentration forecasting would be a useful tool to complement information about expected air quality in the city. Here, the results of a neural network-based model aimed to forecast maximum values of the 8-hr moving average of CO concentrations for the next day are presented. Forecasts from the neural network model are compared with those produced with linear regressions. The neural network model seems to leave more room to adjust free parameters with 1-yr data to predict the following years values. We have worked with 3 yr of data measured at the monitoring station located in the zone with the worst air quality in the city of Santiago, Chile.

Collisions between a Davydov soliton and lattice solitons

Abstract A molecular chain with intramolecular degrees of freedom that supports both Davydov solitons and lattice solitons is investigated. By simulating collisions between a Davydov soliton and lattice solitons of different energies, it is shown that for lattice solitons of rather low energy, the Davydov soliton is destabilized.

Storage of words in a neural network

Abstract We present a neural network that may be used to store patterns with an especific correlation. It is based on a one-shot learning rule that includes multi-neuron synapses. Dilution of connections is introduced naturally, simplifying the implementation. The model may be related to the human ability to store and retrieve words. Numerical simulations on a small network give an insight into the properties of this type of network.

La privatización de la violencia en Colombia y las AUC: de las autodefensas al paramilitarismo contrainsurgente y criminal

espanolEl articulo se inserta en el debate historiografico acerca de la privatizacion de la violencia presente en la historia colombiana desde el siglo XIX. Sostenemos que las autodefensas devenidas en paramilitares se construyeron en la ultima parte del siglo XX con la complicidad y apoyo de ganaderos, elites locales e integrantes del Ejercito. Ha sido clave la conduccion de mafiosos narcotraficantes federados en las AUC en 1997, que agreden al movimiento popular, la izquierda politica y la poblacion civil, desplegando una estrategia de copamiento del Estado. EnglishThe following article exposes the discussion about violences privatization present in the Colombians history since the 19th Century. We argue that the self-defenses (autodefensas) under the form of paramilitaries who were built in the last part of 20th Century with the complicity and the support of ranchers, local elites and Armys members. The drugtraffickers and mafias conduction who were federated in the AUC has been very important, who do damage to the popular movement, the political left and the civil population in 1997. They are deploying a strategy of State takeover.

Prediction of NO concentrations in the atmosphere of an urban area with heavy traffic

By analyzing NO concentrations in the atmosphere recorded hourly for six months at a point close to an avenue with heavy traffic in the city of Santiago, we show that the combination of prevalent information of this pollutant and meteorological variables may be used as input for a perceptron in order to predict NO concentrations several hours in advance.