Arthur da Costa Almeida

Water Quality Monitoring in Large Reservoirs Using Remote Sensing and Neural Networks

Water quality monitoring in lakes and reservoirs using water samples and laboratorial analysis is expensive and time consuming. The use of artificial neural networks to predict water quality using satellite images shows great potential to make this process faster and at lower costs. This article discusses an indirect method to estimate the concentration of pigments (chlorophyll-a), an optically active parameter in water quality. A model based on artificial neural networks, using radial base functions architecture, was developed to predict Tucuruis Reservoir chlorophyll-a concentrations. As input to the neural networks spectral information from Landsat imagery was used, while pigment concentration were used as output information. To train and validate the model we used data from the years 1987, 1988, 1995, 1999, 2000 and 2004. The tested model showed a correlation coefficient of 0.92 for the estimation of pigment (chlorophyll-a) concentrations, indicating its applicability to predict this water quality parameter.

Estimation of Aboveground Forest Biomass in Amazonia with Neural Networks and Remote Sensing

This paper proposes an integrated methodology for estimating aboveground forest biomass in Amazon region. It is based on remote sensing, artificial neural networks and geographical information systems technologies for achieving confident results with a lesser cost than traditional methods of forest inventory. This methodology was tested and validated in Tucurui Reservoir, Brazil.

Recurrent Self-Organizing Map for Severe Weather Patterns Recognition

Weather patterns recognition is very important to improve forecasting skills regarding severe storm conditions over a given area of the Earth. Severe weather can damage electric and telecommunication systems, besides generating material losses and even losses of life (Cooray et al., 2007; Lo Piparo, 2010; Santos et al., 2011). In especial for the electrical sector, is strategic to recognize weather patterns that may help predict weather caused damages. Severe weather forecast is crucial to reduce permanent damage to the systems equipments and outages in transmission or distribution lines.

Cloud-to-ground lightning observations over the Eastern Amazon region: Subsidies for the protection of electric systems

Cloud-to-ground (CG) lightning variables, space and time distributions near the equator, over Eastern Amazon, were analyzed in this work. Over seven million lightning flash events of this type, detected by a VAISALA sensor network operated by the Brazilian Amazon Protection System (SIPAM) between 2006 and 2008 were processed. The results show the sub-areas of higher frequency of occurrences, as well as the monthly and hourly distributions of CG lightning polarity type, current peak intervals for this region. The regional values of the CG lightning parameters should be taken into consideration on electric and telecommunication systems protection projects, against atmospheric electric discharges in the Amazon Region.

Microcontroller-based electric field measurement system with programmable pre-amplifier and filtering for use in the Amazon region

This paper presents a low-cost system to detect and store lightning waveforms in VLF (3–30khz) or ELF (3–3000Hz) frequencies. The name of the system is: Lightning Detection and Waveforms Storage System (LDWSS). The system consists of a whip antenna with a fully-programmable pre-amplifier and filtering circuit and a microcontroller to process the signal and send the data to a computer where it will be stored and analyzed in the future. A comparison of waveforms stored by the system with those found in the literature and comparisons between the quantity of the detected events and the meteorological conditions for that interval were carried out. Preliminary tests have shown the LDWS to be a promising system for research of lightning in the Amazon.