Armando M. Fernandes

Feasibility of forest-fire smoke detection using lidar

The feasibility and fundamentals of forest fire detection by smoke sensing with single-wavelength lidar are discussed with reference to results of 532-nm lidar measurements of smoke plumes from experimental forest fires in Portugal within the scope of the Gestosa 2001 project. The investigations included tracing smoke-plume evolution, estimating forest-fire alarm promptness, and smoke-plume location by azimuth rastering of the lidar optical axis. The possibility of locating a smoke plume whose source is out of line of sight and detection under extremely unfavourable visibility conditions was also demonstrated. The eye hazard problem is addressed and three possibilities of providing eye-safety conditions without loss of lidar sensitivity (namely, using a low energy-per-pulse and high repetition-rate laser, an expanded laser beam, or eye-safe radiation) are discussed.

Measurement of intra-ring wood density by means of imaging VIS/NIR spectroscopy (hyperspectral imaging)

Abstract This paper reports a novel application of hyperspectral imaging (a spectroscopic technique) for measuring wood density profiles at the growth ring scale. The measurements were performed with a spatial resolution of 79 µm. In the present case, hyperspectral imaging was used to measure wood sample reflectance for light in the wavelength range between 380 and 1028 nm, with a resolution of approximately 0.6 nm. The work was performed with 34 samples collected from 34 trees of Pinus pinea. A total of 34,093 density points were used to create and validate a partial least-squares (PLS) regression that converts spectroscopic reflectance data into density values. The coefficient of determination value between the present method and X-ray microdensitometry is 0.810 with a root mean squared error of 6.54×10-2 g.cm-3.

Design of committee machines for classification of single-wavelength lidar signals applied to early forest fire detection

The application of committee machines composed of single-layer perceptrons for the automatic classification of lidar signals for early forest fire detection is analysed. The patterns used for classification are composed of normalised lidar curve segments, pre-processed in order to reduce noise. In contrast to the approach used in previous work, these patterns contain application-specific parameters, such as peak-to-noise ratio (PNR), average amplitude ratio (AvAR) and maximum amplitude ratio (MAR), in order to improve classification efficiency. Using this method a smoke signature detection efficiency of 93% and a false alarm percentage of 0.041% were achieved for small bonfires, using an optimised committee machine composed of four single-layer perceptrons. The same committee machine was able to detect 70% of the smoke signatures in lidar return signals from large-scale fires in an early stage of development. The possibility of using a second committee machine for detecting fully developed large-scale fires is discussed.

Eye-safe lidar measurements for detection and investigation of forest-fire smoke

The problem of eye safety in lidar-assisted wildland fire detection and investigation is considered as a problem of reduction of the hazard range within which the laser beam is dangerous for direct eye exposure. The dependence of this hazard range on the lidar characteristics is examined and possible eye-safety measures discussed. The potential of one of the cheapest ways of providing eye safety, which is based on placing the lidar in an elevated position and using a 1064-nm laser beam with increased divergence, is also investigated experimentally. It is demonstrated that a lidar system operating with wider beams maintains its ability to detect smoke plumes efficiently. Providing eye-safe conditions allows scanning of the internal 3D structure of smoke plumes in the vicinity of fire plots. Examples are given as layer-by-layer smoke concentration plots on the topographic map.

Automatic discrimination of grapevine ( Vitis vinifera L.) clones using leaf hyperspectral imaging and partial least squares

This work was supported by European Union Funds (FEDER/COMPETE – Operational Competitiveness Programme) and by national funds (FCT – Portuguese Foundation for Science and Technology) under the project FCOMP-01-0124-FEDER-022692.

Neural Network Based Recognition of Smoke Signatures from Lidar Signals

The automatic recognition of smoke signatures in lidar signals collected during very small-scale experimental forest fires using neural-network algorithms was studied. An algorithm for pre-processing of raw lidar signals is proposed, which selects suspicious backscattering peaks and makes them unbiased and scale independent. The resulting patterns can be successfully classified as corresponding to alarm or no-alarm conditions by a neural-network algorithm based on a simple one-neuron structure (perceptron). In the case of an alarm, the pre-processing algorithm provides the location of the smoke plume. Five algorithms selected from the literature, and one that was specially developed, all with learning rate adaptation, were used for training the perceptron. Their efficiencies and statistical properties were compared. The best perceptron classifier presented an efficiency of 97% in the classification of smoke-signature patterns and a false alarm rate of 0.9%.

Determination of sugar content in whole Port Wine grape berries combining hyperspectral imaging with neural networks methodologies

The potential of hyperspectral imaging combined with machine learning algorithms to measure sugar content of whole grape berries is presented, as a starting point for developing generalized and flexible frameworks to estimate enological parameters in wine grape berries. In this context, to evaluate the generalization ability of the used machine learning procedure, two neural networks were trained with different training data to compare the performance of each one when tested with the same data set. Six whole grape berries were used for each sample to draw the hyperspectral spectrum in reflectance mode between 308 and 1028 nm. The sugar content was estimated from the spectra using feedforward multiplayer perceptrons in two different neural networks trained each one with a data set from a different year (2012 & 2013); the validation for both neural networks was done by n-fold cross-validation, and the test set used was from 2013. The test set revealed R2 values of 0.906 and RMSE of 1.165 °Brix for the neural network trained with 2012 data and R2 of 0.959 and RMSE of 1.026 °Brix for the 2013 training data neural network. The results obtained indicate that both neural networks present good results and that the 2012 training data neural network exhibits a good performance when compared with the other NN, suggesting that the approach is robust since a generalization (without further training) over years may be obtainable.

BacHBerry: BACterial Hosts for production of Bioactive phenolics from bERRY fruits

BACterial Hosts for production of Bioactive phenolics from bERRY fruits (BacHBerry) was a 3-year project funded by the Seventh Framework Programme (FP7) of the European Union that ran between November 2013 and October 2016. The overall aim of the project was to establish a sustainable and economically-feasible strategy for the production of novel high-value phenolic compounds isolated from berry fruits using bacterial platforms. The project aimed at covering all stages of the discovery and pre-commercialization process, including berry collection, screening and characterization of their bioactive components, identification and functional characterization of the corresponding biosynthetic pathways, and construction of Gram-positive bacterial cell factories producing phenolic compounds. Further activities included optimization of polyphenol extraction methods from bacterial cultures, scale-up of production by fermentation up to pilot scale, as well as societal and economic analyses of the processes. This review article summarizes some of the key findings obtained throughout the duration of the project.

Comparison of eye-safe UV and IR lidar for small forest-fire detection

Lidar is a promising tool for forest-fire monitoring because this active detection technique allows efficient location of tenuous smoke plumes resulting from forest fires at their early stages. For the technique to be generally usable instrumentation must be eye-safe, i.e. it must operate within the spectral range λ<0.4 or λ>1.4 micrometers . In this paper the lidar efficiency at the wavelengths 0.3472 micrometers (second harmonic of the ruby laser) and 1.54 micrometers (Er:glass laser) are compared using a theoretical model. The results of calculations show that the energy required for smoke-plume detection using 0.3472 micrometers becomes greater than the corresponding value for 1.54 micrometers when the distance exceeds some threshold, which ranges between 2 and 6 km depending on other parameters. Being caused by relatively higher absorption of the UV radiation in the atmosphere, this result is valid for any wavelength in the vicinity of 0.35 micrometers , for example, the third harmonic of Nd:YAG laser and the second harmonic of Ti:sapphire laser.

Characterization of neural network generalization in the determination of pH and anthocyanin content of wine grape in new vintages and varieties

The generalization ability of hyperspectral imaging combined with neural networks (NN) in estimating pH and anthocyanin content during ripening was evaluated for vintages and varieties not employed in the NN creation. A NN, from a previously published work, trained with grape samples of Touriga Franca (TF) variety harvested in 2012 was tested with TF from 2013 and two new varieties, Touriga Nacional (TN) and Tinta Barroca (TB) from 2013. Each sample contained a small number of whole berries. The present work results suggest that, under certain conditions, it might be possible for the NN to provide for new vintages and varieties results comparable to those of the vintages and varieties employed in the NN training. For pH, the results are state-of-the-art for the new vintage and varieties tested. For anthocyanin, generalization is bad for TB from 2013 but presents state-of-the-art absolute percentage error for TF and TN from 2013.