A method is presented to estimate photopollution (a.k.a night-lights pollution) in a macroscopic manner, i.e. that can be applied globally, using open-domain data. Photopollution has two components, direct illumination and skyglow i.e. the diffused scattering of light in the atmosphere. The proposed method is currently focusing on direct illumination only. The novelty is that viewshed analysis is deployed, taking into account the viewing distance as well as the amount of the light at each source. Moreover, monthly variation of photopollution is measured based on recently available suitable data.
Night-lights obtained by the DMSP/OLS sensor offer a unique opportunity to measure urban expansion in the past two decades. We apply a method to project the existing night-lights time series in the future in order to forecast urban expansion. The rapidly expanding Moscow city in the Russian Federation is selected as the case study. Night-lights are projected up to the year 2025 by exponential smoothing. It is demonstrated by the results that the method can be used to obtain both spatially explicit, i.e. actual maps, as well as synoptic forecasts, e.g. by means of forecast variables such as the Sum of Lights (SoL). These forecasts are accompanied by estimation of confidence intervals, providing upper and lower bounds for future values. The method presented can be applied globally.
Neural networks have received much attention in the field of remote sensing. Topology identification remains however
one of the major difficulties in the efficient application of neural networks. Currently, topology determination is based
on trial and error, on heuristics that amalgamate past experience and on weight pruning algorithms. It is argued in this
paper that global search methods such as genetic algorithms can be deployed in discovering near optimal network
topologies. An example on multisource classification for land cover mapping is presented. The results indicate that the
global search paradigm is worth further exploration especially now that computing becomes more and more powerful.
In this paper computational intelligence, referring here to the synergy of neural networks and genetic algorithms, is deployed in order to determine a near-optimal neural network for the classification of dark formations in oil spills and look-alikes. Optimality is sought in the framework of a multi-objective problem, i.e. the minimization of input features used and, at the same time, the maximization of overall testing classification accuracy. The proposed method consists of two concurrent actions. The first is the identification of the subset of features that results in the highest classification accuracy on the testing data set i.e. feature selection. The second parallel process is the search for the neural network topology, in terms of number of nodes in the hidden layer, which is able to yield optimal results with respect to the selected subset of features. The results show that the proposed method, i.e. concurrently evolving features and neural network topology, yields superior classification accuracy compared to sequential floating forward selection as well as to using all features together. The accuracy matrix is deployed to show the generalization capacity of the discovered neural network topology on the evolved sub-set of features.