Search

Abstract Stress in sea urchins leads to high mortality and economic losses in both the environment and aquaculture. The green sea urchin Strongylocentrotus droebachiensis has been documented emitting complex biofluorescence, yet how this responds to external stressors is unknown. Adult sea urchins (n = 210) were divided between control (n = 30) and experimental groups (n = 180), using three transport variables: out of water, in water at elevated temperatures, (warm-water) and in water at seawater temperature (cold-water). Hyperspectral imaging of external fluorescence and fluorospectrometric analysis on coelomic fluid was measured at five intervals (hour 0,3,6,9,12). External green emissions (∼580 nm) responded to all treatments, peaking at h9. External red emissions (∼680–730 nm) in the cold-water remained low until an h9 peak. The warm water increased emissions at each interval, peaking at h9. The out of water gradually increased, with the highest at h12. The coelomic fluid fluorescence (∼680 nm) was low to nonexistent except in warm-water, whose elevated levels suggest that fluorescent emissions are a measurable byproduct of internal adaptation(s) to stress. Early detection of fluorescent emissions (broken spines, lesions) may prevent economic losses. The observed link between fluorescence and the applied stressors provides a baseline for developing non-invasive technology for improving echinoderm welfare.

Abstract Parasites in fish muscle present a significant problem for the seafood industry in terms of both quality and health and safety, but the low contrast between parasites and fish tissue makes them exceedingly difficult to detect. The traditional method to identify nematodes requires removing fillets from the production line for manual inspection on candling tables. This technique is slow, labor intensive and typically only finds about half the parasites present. The seafood industry has struggled for decades to develop a method that can improve the detection rate while being performed in a rapid, non-invasive manner. In this study, a newly developed solution uses deep neural networks to simultaneously analyze the spatial and spectral information of hyperspectral imaging data. The resulting technology can be directly integrated into existing industrial processing lines to rapidly identify nematodes at detection rates (73%) better than conventional manual inspection (50%).

Dirofilaria immitis is a mosquito-borne nematode of dogs, other carnivores and, occasionally, humans. Globally, D. immitis infection (which causes heartworm) is typically more prevalent in tropical than temperate regions. In this study, the seroprevalence of D. immitis was determined from a sample of 335 non-stray dogs from four municipalities, two each from the states of Puebla and Guerrero in Mexico, using polyclonal antibodies to detect serum antigens using an enzyme-linked immunosorbent assay (ELISA). The accuracy of the assay was compared with the modified Knott’s test. The polyclonal antibody used in the direct ELISA had a high sensitivity (100%) with variable specificity (98.2–98.8%) in the municipalities of Puebla and Guerrero. The area under the curve for the four municipalities was 1.0, indicating a high accuracy test, with a cut-off value ranging from 0.45 to 0.50. The overall prevalence of D. immitis infection was 17.56% (59 out of 335). The highest prevalence was in Acapulco (24.78%), followed by Chilpancingo (20.93%), Tecamachalco (10.81%) and Quecholac (8.06%). The highest percentage of positive samples was detected in tropical regions (23.12%) and the lowest in temperate regions (9.56%). This study demonstrates that polyclonal anti-D. immitis antibodies can successfully diagnose heartworm-infected dogs and be used to monitor prevalence effectively and develop prevention strategies against Dirofilaria infection.

Abstract Hyperspectral imaging has demonstrated its potential to provide correlated spatial and spectral information of a sample by a non‐contact and non‐invasive technology. In the medical field, especially in histopathology, HSI has been applied for the classification and identification of diseased tissue and for the characterization of its morphological properties. In this work, we propose a hybrid scheme to classify non‐tumor and tumor histological brain samples by hyperspectral imaging. The proposed approach is based on the identification of characteristic components in a hyperspectral image by linear unmixing, as a features engineering step, and the subsequent classification by a deep learning approach. For this last step, an ensemble of deep neural networks is evaluated by a cross‐validation scheme on an augmented dataset and a transfer learning scheme. The proposed method can classify histological brain samples with an average accuracy of 88%, and reduced variability, computational cost, and inference times, which presents an advantage over methods in the state‐of‐the‐art. Hence, the work demonstrates the potential of hybrid classification methodologies to achieve robust and reliable results by combining linear unmixing for features extraction and deep learning for classification.

Abstract Hyperspectral (HS) imaging (HSI) technology combines the main features of two existing technologies: imaging and spectroscopy. This allows to analyse simultaneously the morphological and chemical attributes of the objects captured by a HS camera. In recent years, the use of HSI provides valuable insights into the interaction between light and biological tissues, and makes it possible to detect patterns, cells, or biomarkers, thus, being able to identify diseases. This work presents the HistologyHSI-GB dataset, which contains 469 HS images from 13 patients diagnosed with brain tumours, specifically glioblastoma. The slides were stained with haematoxylin and eosin (H&E) and captured using a microscope at 20× power magnification. Skilled histopathologists diagnosed the slides and provided image-level annotations. The dataset was acquired using custom HSI instrumentation, consisting of a microscope equipped with an HS camera covering the spectral range from 400 to 1000 nm.

Abstract The demand for lumpfish (Cyclopterus lumpus) as a biological control for salmon lice is increasing. However, lumpfish welfare is considered a limiting factor within aquaculture operations. Identifying a noninvasive parameter that measures subclinical stress in lumpfish is a key goal for improving their welfare. The lumpfish is documented to emit green and red biofluorescence within the blue shifted light of their environment. Here we show that lumpfish fluorescence responds to a therapeutic stressor within a controlled experiment. Lumpfish (n = 60) underwent a 3-h freshwater bath therapeutant to evaluate whether fluorescence spectra produced by the species respond to external stimuli. Lumpfish were quickly scanned under a hyperspectral camera (400–1000 nm spectral range) prior to and after treatment. The lumpfish were randomly divided into 3 groups with identical treatment. All groups increased fluorescence emissions, though the level of change depended on whether the averaged, red, or green spectra were analyzed; the control group (n = 20) remained constant. All lumpfish emitted green fluorescence (~ 590–670 nm) while a portion (49%) produced red fluorescence (~ 690–800 nm). As lumpfish fluorescence shifts in response to the applied stressor, this study provides insight into how fluorescence may be incorporated into the welfare management of lumpfish.

Accurate assessment of evapotranspiration (ETa) and crop coefficient (Kc) is crucial for optimizing irrigation practices in water-scarce regions. While satellite-based surface energy balance models offer a promising solution, their application to sparse canopies like apple orchards requires specific validation. This study investigated the spatial and temporal dynamics of ETa and Kc in a drip-irrigated ‘Pink Lady’ apple orchard under Mediterranean conditions over three growing seasons (2012/13, 2013/14, 2014/15). The METRIC model, incorporating calibrated sub-models for leaf area index (LAI), surface roughness (Zom), and soil heat flux (G), was employed to estimate ETa and Kc. These estimates were validated against field-scale Eddy Covariance data. Results indicated that METRIC overpredicted Kc and ETa with errors less than 10 %. These findings highlight the potential of the calibrated METRIC model as a valuable decision-making tool for irrigation management in apple orchards.

Actual evapotranspiration (ETa) can be commonly estimated using numerical models based on i) weather and plant-based parameters, ii) from remotely sensed data and energy balance algorithms, and lately, iii) through the development and implementation of machine learning (ML) modeling techniques. In this work, supervised ML models were developed from a vineyard located in Talca, Chile, (i) to estimate actual evapotranspiration (ETa) (Model 1; M1) using the micrometeorological approach [Eddy Covariance; EC; sensible (H), latent (LE), soil heat fluxes (G) and net radiation (Rn)] and data from an automatic meteorological station (AMS) in reference conditions as ground-truth (inputs); (ii) to estimate energy balance components (Model 2; M2) from AMS data (inputs) and EC energy balance data as targets; (iii) to estimate ETa from the EC’s measured ETa data as target and thermal time data (degree hours; DH) calculated from air temperature with a base of 5 °C increments from 5 – 45 °C as inputs (Model 3; M3) and iv) to estimate energy balance components (targets from EC) from the same inputs of Model 3 (Model 4; M4). Results showed that the developed ML models had high accuracy and performance with no signs of over or under-fitting with a high correlation (R) and slope (b) close to unity (M1; R=0.94; b=0.89; M2; R=0.97; b=0.93; M3; R=0.97; b=0.89–0.95; M4; R=0.98; b=0.97). Furthermore, models were directly deployed over another vineyard located 22 km West of the modeled vineyard at 60 m lower over the sea level with significant performances and R values (R = 0.64–0.87; b = 0.66–1.00 for M1 to M4, respectively). These models could be used for precision irrigation to increase water use efficiency and better control canopy vigor, balance fruit and vegetative components, and ultimately improve berry and wine quality traits.

Given the complexity of integrating and forecasting the interconnected effects of body size, population dynamics, and energy availability, theoretical approaches that link ecological and computational knowledge are required. Individual attributes, such as body size, exert influence and are, in turn, influenced by community structure. Distinguishing between the processes that generate population patterns and making predictions poses a challenge in theoretical ecology, drawing on concepts ranging from traditional natural philosophy to contemporary physical sciences. To address this challenge, our research proposes a computational model for conducting theoretical-exploratory simulations of a biological community, incorporating body size, density, and population dynamics based on the Metabolic Theory of Ecology principles. This community includes reproductive and non-reproductive individuals transitioning between feeding and reproductive areas. Accounting for seasonal limits and finite energy, we delineate the dynamic relationship between body size and population abundance. Additionally, we present a temporal simulation of allometric exponents describing the density pattern. The findings highlight the importance of considering energetic limitations to maintain the relationship between body size and population density and present the possibility of temporally modeling the allometric exponent of this demographic pattern.

Abstract Brain surgery is one of the most common and effective treatments for brain tumour. However, neurosurgeons face the challenge of determining the boundaries of the tumour to achieve maximum resection, while avoiding damage to normal tissue that may cause neurological sequelae to patients. Hyperspectral (HS) imaging (HSI) has shown remarkable results as a diagnostic tool for tumour detection in different medical applications. In this work, we demonstrate, with a robust k-fold cross-validation approach, that HSI combined with the proposed processing framework is a promising intraoperative tool for in-vivo identification and delineation of brain tumours, including both primary (high-grade and low-grade) and secondary tumours. Analysis of the in-vivo brain database, consisting of 61 HS images from 34 different patients, achieve a highest median macro F1-Score result of 70.2 ± 7.9% on the test set using both spectral and spatial information. Here, we provide a benchmark based on machine learning for further developments in the field of in-vivo brain tumour detection and delineation using hyperspectral imaging to be used as a real-time decision support tool during neurosurgical workflows.

Abstract Atmospheric longwave downward radiation (L d) is one of the significant components of net radiation (Rn), and it drives several essential ecosystem processes. L d can be estimated with simple empirical methods using atmospheric emissivity (εa) submodels. In this study, eight global models for εa were evaluated, and the best-performing model was calibrated on a global scale using a parametric instability analysis approach. The climatic data were obtained from a dynamically consistent scale resolution of basic atmospheric quantities and computed parameters known as NCEP/NCAR reanalysis (NNR) data. The performance model was evaluated with monthly average values from the NNR data. The Brutsaert equation demonstrated the best performance, and then it was calibrated. The seasonal global trend of the Brutsaert equation calibrated coefficient ranged between 1.2 and 1.4, and the K-means analysis identified five homogeneous zones (clusters) with similar behavior. Finally, the calibrated Brutsaert equation improved the Rn estimation, with an error reduction, at the worldwide scale, of 64%. Meanwhile, the error reduction for each cluster ranged from 18 to 77%. Hence, Brutsaert’s equation coefficient should not be considered a constant value for use in εa estimation, nor in time or location.

Fasciolosis, a globally re-emerging zoonotic disease, is mostly caused by the parasitic infection with Fasciola hepatica, often known as the liver fluke. This disease has a considerable impact on livestock productivity. This study aimed to evaluate the fluke burdens and faecal egg counts in goats that were administered phage clones of cathepsin L mimotopes and then infected with F. hepatica metacercariae. Additionally, the impact of vaccination on the histology of the reproductive system, specifically related to egg generation in adult parasites, was examined. A total of twenty-four goats, which were raised in sheds, were divided into four groups consisting of six animals each. These groups were randomly assigned. The goats were then subjected to two rounds of vaccination. Each vaccination involved the administration of 1 × 1013 phage particles containing specific mimotopes for cathepsin L2 (group 1: PPIRNGK), cathepsin L1 (group 2: DPWWLKQ), and cathepsin L1 (group 3: SGTFLFS). The immunisations were carried out on weeks 0 and 4, and the Quil A adjuvant was used in combination with the mimotopes. The control group was administered phosphate-buffered saline (PBS) (group 4). At week 6, all groups were orally infected with 200 metacercariae of F. hepatica. At week 22 following the initial immunisation, the subjects were euthanised, and adult F. hepatica specimens were retrieved from the bile ducts and liver tissue, and subsequently quantified. The specimens underwent whole-mount histology for the examination of the reproductive system, including the testis, ovary, vitellaria, Mehlis’ gland, and uterus. The mean fluke burdens following the challenge were seen to decrease by 50.4%, 62.2%, and 75.3% (p < 0.05) in goats that received vaccinations containing cathepsin L2 PPIRNGK, cathepsin L1 DPWWLKQ, and cathepsin L1 SGTFLFS, respectively. Animals that received vaccination exhibited a significant reduction in the production of parasite eggs. The levels of IgG1 and IgG2 isotypes in vaccinated goats were significantly higher than in the control group, indicating that protection is associated with the induction of a mixed Th1/Th2 immune response. The administration of cathepsin L to goats exhibits a modest level of efficacy in inducing histological impairment in the reproductive organs of liver flukes, resulting in a reduction in egg output.

Abstract We investigate the balance of radiation and energy over a lime orchard in Eastern Amazon and how it relates to environmental conditions. We found that lime trees aged between 6 and 7 years old reflect 11.0% to 14.5% of incoming shortwave radiation, and the latent heat flux corresponds to 57.6% and 66.6% of the daily net radiation in the dry season (August - November) of 2020, and 2021, respectively. The soil heat flux represents 1% to 2% of the daily net radiation. Evapotranspiration was much lower than the reference evapotranspiration from August to November in 2019 and 2020. Evapotranspiration increased proportionally to the reference evapotranspiration from August to November 2021. This increase may be explained by weather conditions, such as the frequent rainfall during the dry season of 2021, in the same period when the energy for evapotranspiration is higher. Also, the high relative humidity between August and November 2021 may have favored the opening of stomata, increasing the orchard's evapotranspiration. The crop coefficient ranges between 0.74 and 0.84.

In recent years, cases of vasskveite (water halibut) syndrome in halibut have been increasing. At the moment, there exists no way to screen for the syndrome immediately after capture, which is problematic for both exporters and purchasers. In this article, we compared good quality halibut and halibut exhibiting the syndrome using a variety of techniques. Hyperspectral imaging was used to quantify the relative amounts of fat and water in the tissue. Diffusion tensor imaging was used to characterize tissue structure. Histology was performed to provide direct visual characterization of the tissue. Results indicate the muscle fibers in afflicted fish exhibit disordered growth and the tissue is lacking in fat. These results are in line with the current theory that the syndrome stems from a nutritional deficiency in the halibut diet. Hyperspectral imaging appears to be a promising technology to rapidly identify afflicted halibut immediately after capture.

Remote sensing technology is widely used to obtain evapotranspiration (ETa), but whether it can distinguish the differences in farmland energy balance components and ETa under different irrigation methods has not been studied. We used Landsat 8 data as the primary dataset to drive the METRIC model and inverted the surface parameters and ETa of the Shiyang River Basin from 2014 to 2018. After improving the METRIC model using Ta obtained by the regression method instead of interpolation to calculate the net radiation flux (Rn), R2 was improved from 0.45 to 0.53, and the RMSE was reduced from 61 W/m2 to 51 W/m2. The ETa estimation results on satellite overpass days performed well, with R2 equal to 0.93 and RMSE equal to 0.48 mm when compared with the Eddy covariance method (EC) observations. Subsequently, the different growth stages and daily average ETa estimates of maize were compared with three observations (water balance, WB; Bowen ratio and energy balance method, BREB; and EC). The daily estimates of ETa correlate well with the observations of BREB (R2BI = 0.82, R2DI = 0.92; RMSEBI = 0.46 mm/day, RMSEDI = 0.32 mm/day) and EC (R2BI = 0.85, R2DI = 0.92; RMSEBI = 0.45 mm/day, RMSEDI = 0.34 mm/day), and the estimation for drip irrigation was found to be better than for border irrigation. The total accuracy of the ETa estimation on the five-year overpass day of maize farmland reached R2 = 0.93 and RMSE = 0.48 mm. With sufficient remote sensing data, the 4-year average ETa of maize was 31 mm lower for DI than for BI, and the mean value of ETa obtained from the three observation methods was 40 mm. The METRIC model can be used to distinguish ETa differences between the two irrigation methods in maize farmlands.

The Scholander-type pressure chamber to measure midday stem water potential (MSWP) has been widely used to schedule irrigation in commercial vineyards. However, the limited number of sites that can be evaluated using the pressure chamber makes it difficult to evaluate the spatial variability of vineyard water status. As an alternative, several authors have suggested using the crop water stress index (CWSI) based on low-cost thermal infrared (TIR) sensors to estimate the MSWP. Therefore, this study aimed to develop a low-cost wireless infrared sensor network (WISN) to monitor the spatial variability of MSWPs in a drip-irrigated Cabernet Sauvignon vineyard under two levels of water stress. For this study, the MLX90614 sensor was used to measure canopy temperature (Tc), and thus compute the CWSI. The results indicated that good performance of the MLX90614 infrared thermometers was observed under laboratory and vineyard conditions with root mean square error (RMSE) and mean absolute error (MAE) values being less than 1.0 °C. Finally, a good nonlinear correlation between the MSWP and CWSI (R2 = 0.72) was observed, allowing the development of intra-vineyard spatial variability maps of MSWP using the low-cost wireless infrared sensor network.

Abstract Currently, intraoperative guidance tools used for brain tumor resection assistance during surgery have several limitations. Hyperspectral (HS) imaging is arising as a novel imaging technique that could offer new capabilities to delineate brain tumor tissue in surgical-time. However, the HS acquisition systems have some limitations regarding spatial and spectral resolution depending on the spectral range to be captured. Image fusion techniques combine information from different sensors to obtain an HS cube with improved spatial and spectral resolution. This paper describes the contributions to HS image fusion using two push-broom HS cameras, covering the visual and near-infrared (VNIR) [400–1000 nm] and near-infrared (NIR) [900–1700 nm] spectral ranges, which are integrated into an intraoperative HS acquisition system developed to delineate brain tumor tissue during neurosurgical procedures. Both HS images were registered using intensity-based and feature-based techniques with different geometric transformations to perform the HS image fusion, obtaining an HS cube with wide spectral range [435–1638 nm]. Four HS datasets were captured to verify the image registration and the fusion process. Moreover, segmentation and classification methods were evaluated to compare the performance results between the use of the VNIR and NIR data, independently, with respect to the fused data. The results reveal that the proposed methodology for fusing VNIR–NIR data improves the classification results up to 21% of accuracy with respect to the use of each data modality independently, depending on the targeted classification problem.

Evapotranspiration (ET) is an essential part of energy flow between the surface of the earth and the atmosphere, simultaneously involving the water, carbon, and energy cycles. It is mainly determined by climate, land use, and land cover changes. Additionally, there is still a need for quantitative characterization of the impacts of climate factors and human activities on ET and regional water resource efficiency in arid and semiarid regions. Based on Landsat-8 remote sensing imagery and land use data, the crop planting structures in the Liangzhou District of the middle reaches of the Shiyang River Basin were identified using a multiband and multi-temporal approach in this study. Subsequently, the ET of major cash crops was inverted using the three-temperature model. This research quantitatively describes the responses of wheat and corn to the climate and human activities over a two-year period. Furthermore, the impact of crop planting structures and climatic factors on ET was elucidated. The results indicate that a combination of multi-temporal green and shortwave infrared 1 bands is the optimal spectral combination to extract the planting structures. Compared to 2019, the wheat area decreased by 23.27% in 2020, while the corn area increased by 5.96%. Both crops exhibited significant spatial heterogeneity in ET during the growing season. The typical daily range of ET for wheat was 0.4–7.2 mm/day, and for corn, it was 1.5–4.0 mm/day. Among the climatic factors, temperature showed the highest correlation with ET (R = 0.80, p ≤ 0.05). Our research findings provide valuable insights for the fine identification of crop planting structures and a better understanding of the response of ET to climatic factors and planting structures.

The culture of açaí (Euterpe oleraceae M.), originating from floodplain areas, was planted on dry land in many properties in Pará, Brazil, making necessary the use of irrigation. To irrigate adequately with less waste, it is necessary that studies aim at increasing efficiency in the use of water in this sector, and one of the ways to do so is to estimate evapotranspiration (ET). The objective of this study was to estimate the actual daily evapotranspiration using the Surface Energy Balance Algorithm for Land (SEBAL) in eastern Amazonia. Six images from the Landsat 8 satellite were used, and the estimates of evapotranspiration with the SEBAL algorithm showed good agreement with the results obtained by the Bowen ratio method in the area of açaí planting, including the mean absolute error (MAE), mean relative error (MRE), root of mean square error (RMSE), and the concordance index (d index) equal to 0.45 mm day−1, 4.23%, 0.52 mm day−1, and 0.80, respectively. SEBAL showed the ability to distinguish the soil cover, demonstrating the sensitivity of the model, which provided the mapping of the components analyzed. The use of the algorithm helps in decision making regarding irrigation management and reducing costs and water losses.

Several causes make brain cancer identification a challenging task for neurosurgeons during the surgical procedure. The surgeons' naked eye sometimes is not enough to accurately delineate the brain tumor location and extension due to its diffuse nature that infiltrates in the surrounding healthy tissue. For this reason, a support system that provides accurate cancer delimitation is essential in order to improve the surgery outcomes and hence the patient's quality of life. The brain cancer detection system developed as part of the “HypErspectraL Imaging Cancer Detection” (HELICoiD) European project meets this requirement exploiting a non-invasive technique suitable for medical diagnosis: the hyperspectral imaging (HSI). A crucial constraint that this system has to satisfy is providing a real-time response in order to not prolong the surgery. The large amount of data that characterizes the hyperspectral images, and the complex elaborations performed by the classification system make the High Performance Computing (HPC) systems essential to provide real-time processing. The most efficient implementation developed in this work, which exploits the Graphic Processing Unit (GPU) technology, is able to classify the biggest image of the database (worst case) in less than three seconds, largely satisfying the real-time constraint set to 1 minute for surgical procedures, becoming a potential solution to implement hyperspectral video processing in the near future.

Hyperspectral Imaging (HSI) is increasingly adopted in medical applications for the usefulness of understanding the spectral signature of specific organic and non-organic elements. The acquisition of such images is a complex task, and the commercial sensors that can measure such images is scarce down to the point that some of them have limited spatial resolution in the bands of interest. This work proposes an approach to enhance the spatial resolution of hyperspectral histology samples using super-resolution. As the data volume associated to HSI has always been an inconvenience for the image processing in practical terms, this work proposes a relatively low computationally intensive algorithm. Using multiple images of the same scene taken in a controlled environment (hyperspectral microscopic system) with sub-pixel shifts between them, the proposed algorithm can effectively enhance the spatial resolution of the sensor while maintaining the spectral signature of the pixels, competing in performance with other state-of-the-art super-resolution techniques, and paving the way towards its use in real-time applications.

Water relations in vineyards have been largely studied; giving insides regarding the way grapevine interacts with its environment according to water availability, providing us terminologies like Isohydric and Anisohydric, which have been applied to categorize cultivars and rootstocks. Recently, the use of this terminology has been subjected to discussion regarding its use as a category to describe and separate grapevine cultivars instead of using it as a continuous, where grapevines can behave more iso or anysohidric depending on the environment where they are grown. In this study, using a deficit irrigation (RDI) trial in a commercial vineyard located in Maule Valley in Central Chile, the relationship between Midday Stem Water Potential (ψx), Stomatal Conductance (gs), Soil Water Content (WC), and Vapour Pressure Deficit (VPD) on cv. Cabernet Sauvignon was studied, a grape variety that has been classified as isohydric. The trial was carried out for 3 years from 2018 to 2020 in which four RDI treatments were employed to replenish different portions of evapotranspiration (ET) from pea-size until harvest. These irrigation treatments were conceived as 100% ET, 70% ET, 50-100% ET (50% ET before veraison and 100% ET afterwards) and 35-100% ET (35% ET before veraison and 100% ET afterwards). Findings in this study show how the relationship between ψx and gs is treatment dependent; in treatments where no water deficit was imposed a weaker relationship between the variables was observed, showing a large variation between gs at similar ψx, being gs more dependent on VPD compared to the treatments with a larger deficit on its irrigation. As the deficit irrigation increased, grapevines started to shift to a smaller variation on its gs over large variations on its ψx. This result shows that irrigation management and deficit irrigation strategies impact the way plants react to water availability and leads to different behavior on its gs/ψx relationship.

Near-surface air (Ta) and land surface (Ts) temperatures are essential parameters for research in the fields of agriculture, hydrology, and ecological changes, which require accurate datasets with different temporal and spatial resolutions. However, the sparse spatial distribution of meteorological stations in Northwest China may not effectively provide high-precision Ta data. And it is not clear whether it is necessary to improve the accuracy of Ts which has the most influence on Ta. In response to this situation, the main objective of this study is to estimate Ta for Northwest China using multiple linear regression models (MLR) and random forest (RF) algorithms, based on Landsat 8 images and auxiliary data collected from 2014 to 2019. Ts, NDVI (Normalized Difference Vegetation Index), surface albedo, elevation, wind speed, and Julian day were variables to be selected, then used to estimate the daily average Ta after analysis and adjustment. Also, the Radiative Transfer Equation (RTE) method for calculating Ts would be corrected by NDVI (RTE-NDVI). The results show that: 1) The accuracy of the surface temperature (Ts) was improved by using RTE-NDVI; 2) Both MLR and RF models are suitable for estimating Ta in areas with few meteorological stations; 3) Analyzing the temporal and spatial distribution of errors, it is found that the MLR model performs well in spring and summer, and is lower in autumn, and the accuracy is higher in plain areas away from mountains than in mountainous areas and nearby areas. This study shows that through appropriate selection and combination of variables, the accuracy of estimating the pixel-scale Ta from satellite remote sensing data can be improved in the area that has less meteorological data.

Currently, one of the most common causes of death worldwide is cancer. The development of innovative methods to support the early and accurate detection of cancers is required to increase the recovery rate of patients. Several studies have shown that medical Hyperspectral Imaging (HSI) combined with artificial intelligence algorithms is a powerful tool for cancer detection. Various preprocessing methods are commonly applied to hyperspectral data to improve the performance of the algorithms. However, there is currently no standard for these methods, and no studies have compared them so far in the medical field. In this work, we evaluated different combinations of preprocessing steps, including spatial and spectral smoothing, Min-Max scaling, Standard Normal Variate normalization, and a median spatial smoothing technique, with the goal of improving tumor detection in three different HSI databases concerning colorectal, esophagogastric, and brain cancers. Two machine learning and deep learning models were used to perform the pixel-wise classification. The results showed that the choice of preprocessing method affects the performance of tumor identification. The method that showed slightly better results with respect to identifing colorectal tumors was Median Filter preprocessing (0.94 of area under the curve). On the other hand, esophagogastric and brain tumors were more accurately identified using Min-Max scaling preprocessing (0.93 and 0.92 of area under the curve, respectively). However, it is observed that the Median Filter method smooths sharp spectral features, resulting in high variability in the classification performance. Therefore, based on these results, obtained with different databases acquired by different HSI instrumentation, the most relevant preprocessing technique identified in this work is Min-Max scaling.

Cancer originates from the uncontrolled growth of healthy cells into a mass. Chromophores, such as hemoglobin and melanin, characterize skin spectral properties, allowing the classification of lesions into different etiologies. Hyperspectral imaging systems gather skin-reflected and transmitted light into several wavelength ranges of the electromagnetic spectrum, enabling potential skin-lesion differentiation through machine learning algorithms. Challenged by data availability and tiny inter and intra-tumoral variability, here we introduce a pipeline based on deep neural networks to diagnose hyperspectral skin cancer images, targeting a handheld device equipped with a low-power graphical processing unit for routine clinical testing. Enhanced by data augmentation, transfer learning, and hyperparameter tuning, the proposed architectures aim to meet and improve the well-known dermatologist-level detection performances concerning both benign-malignant and multiclass classification tasks, being able to diagnose hyperspectral data considering real-time constraints. Experiments show 87% sensitivity and 88% specificity for benign-malignant classification and specificity above 80% for the multiclass scenario. AUC measurements suggest classification performance improvement above 90% with adequate thresholding. Concerning binary segmentation, we measured skin DICE and IOU higher than 90%. We estimated 1.21 s, at most, consuming 5 Watts to segment the epidermal lesions with the U-Net++ architecture, meeting the imposed time limit. Hence, we can diagnose hyperspectral epidermal data assuming real-time constraints.

In some applications of biomedical imaging, a linear mixture model can represent the constitutive elements (end-members) and their contributions (abundances) per pixel of the image. In this work, the extended blind end-member and abundance extraction (EBEAE) methodology is mathematically formulated to address the blind linear unmixing (BLU) problem subject to positivity constraints in optical measurements. The EBEAE algorithm is based on a constrained quadratic optimization and an alternated least-squares strategy to jointly estimate end-members and their abundances. In our proposal, a local approach is used to estimate the abundances of each end-member by maximizing their entropy, and a global technique is adopted to iteratively identify the end-members by reducing the similarity among them. All the cost functions are normalized, and four initialization approaches are suggested for the end-members matrix. Synthetic datasets are used first for the EBEAE validation at different noise types and levels, and its performance is compared to state-of-the-art algorithms in BLU. In a second stage, three experimental biomedical imaging applications are addressed with EBEAE: m-FLIM for chemometric analysis in oral cavity samples, OCT for macrophages identification in post-mortem artery samples, and hyper-spectral images for in-vivo brain tissue classification and tumor identification. In our evaluations, EBEAE was able to provide a quantitative analysis of the samples with none or minimal a priori information.

Currently, the use of hyperspectral imaging (HSI) for the inspection of microscopic samples is an emerging trend in different fields. The use of push-broom hyperspectral (HS) cameras against other HSI technologies is motivated by their high spectral resolution and their capabilities to exploit spectral ranges beyond 1000 nm. Nevertheless, using push-broom cameras in miscroscopes imposes to perform an accurate spatial scanning of the sample to collect the HS data. In this manuscript, we present a methodology to correctly set-up a push-broom HS microscope to acquire high-quality HS images. Firstly, we describe a custom 3D printed mechanical system developed to perform the spatial scanning by producing a precise linear movement of the microscope stage. Then, we discuss how the dynamic range maximisation, the focusing, the alignment and the adequate speed determination affect the overall quality of the images. Finally, we present some examples of HS data showing the most common defects that usually appear when capturing HS images using a push-broom camera, and also a set of images acquired from real microscopic samples.

The use of hyperspectral imaging for medical applications is becoming more common in recent years. One of the main obstacles that researchers find when developing hyperspectral algorithms for medical applications is the lack of specific, publicly available, and hyperspectral medical data. The work described in this paper was developed within the framework of the European project HELICoiD (HypErspectraL Imaging Cancer Detection), which had as a main goal the application of hyperspectral imaging to the delineation of brain tumors in real-time during neurosurgical operations. In this paper, the methodology followed to generate the first hyperspectral database of in-vivo human brain tissues is presented. Data was acquired employing a customized hyperspectral acquisition system capable of capturing information in the Visual and Near InfraRed (VNIR) range from 400 to 1000 nm. Repeatability was assessed for the cases where two images of the same scene were captured consecutively. The analysis reveals that the system works more efficiently in the spectral range between 450 and 900 nm. A total of 36 hyperspectral images from 22 different patients were obtained. From these data, more than 300 000 spectral signatures were labeled employing a semi-automatic methodology based on the spectral angle mapper algorithm. Four different classes were defined: normal tissue, tumor tissue, blood vessel, and background elements. All the hyperspectral data has been made available in a public repository.

Hyperspectral (HS) imaging presents itself as a non-contact, non-ionizing and non-invasive technique, proven to be suitable for medical diagnosis. However, the volume of information contained in these images makes difficult providing the surgeon with information about the boundaries in real-time. To that end, High-Performance-Computing (HPC) platforms become necessary. This paper presents a comparison between the performances provided by five different HPC platforms while processing a spatial-spectral approach to classify HS images, assessing their main benefits and drawbacks. To provide a complete study, two different medical applications, with two different requirements, have been analyzed. The first application consists of HS images taken from neurosurgical operations; the second one presents HS images taken from dermatological interventions. While the main constraint for neurosurgical applications is the processing time, in other environments, as the dermatological one, other requirements can be considered. In that sense, energy efficiency is becoming a major challenge, since this kind of applications are usually developed as hand-held devices, thus depending on the battery capacity. These requirements have been considered to choose the target platforms: on the one hand, three of the most powerful Graphic Processing Units (GPUs) available in the market; and, on the other hand, a low-power GPU and a manycore architecture, both specifically thought for being used in battery-dependent environments.

In recent years, researchers designed several artificial intelligence solutions for healthcare applications, which usually evolved into functional solutions for clinical practice. Furthermore, deep learning (DL) methods are well-suited to process the broad amounts of data acquired by wearable devices, smartphones, and other sensors employed in different medical domains. Conceived to serve the role of diagnostic tool and surgical guidance, hyperspectral images emerged as a non-contact, non-ionizing, and label-free technology. However, the lack of large datasets to efficiently train the models limits DL applications in the medical field. Hence, its usage with hyperspectral images is still at an early stage. We propose a deep convolutional generative adversarial network to generate synthetic hyperspectral images of epidermal lesions, targeting skin cancer diagnosis, and overcome small-sized datasets challenges to train DL architectures. Experimental results show the effectiveness of the proposed framework, capable of generating synthetic data to train DL classifiers.

Due to the proliferation of precision agriculture, the obstacle of estimating evapotranspiration (ET) and its components from shadow pixels acquired from remote sensing technology should not be neglected. To accurately detect shaded soil and leaf pixels and quantify the implications of shadow pixels on ET inversion, a two-year field-scale observation was carried out in the growing season for a pinot noir vineyard. Based on high-resolution remote sensing sensors covering visible light, thermal infrared, and multispectral light, the supervised classification was applied to detect shadow pixels. Then, we innovatively combined the normalized difference vegetation index with the three-temperature model to quantify the proportion of plant transpiration (T) and soil evaporation (E) in the vineyard ecosystem. Finally, evaluated with the eddy covariance system, we clarified the implications of the shadow pixels on the ET estimation and the spatiotemporal patterns of ET in a vineyard system by considering where shadow pixels were presented. Results indicated that the shadow detection process significantly improved reliable assessment of ET and its components. (1) The shaded soil pixels misled the land cover classification, with the mean canopy cover ignoring shadows 1.68–1.70 times more often than that of shaded area removal; the estimation accuracy of ET can be improved by 4.59–6.82% after considering the effect of shaded soil pixels; and the accuracy can be improved by 0.28–0.89% after multispectral correction. (2) There was a 2 °C canopy temperature discrepancy between sunlit leaves and shaded leaves, meaning that the estimation accuracy of T can be improved by 1.38–7.16% after considering the effect of shaded canopy pixels. (3) Simultaneously, the characteristics showed that there was heterogeneity of ET in the vineyard spatially and that E and T fluxes accounted for 238.05 and 208.79 W·m−2, respectively; the diurnal variation represented a single-peak curve, with a mean of 0.26 mm/h. Our findings provide a better understanding of the influences of shadow pixels on ET estimation using remote sensing techniques.

Hyperspectral Imaging (HSI) techniques have demonstrated potential to provide useful information in a broad set of applications in different domains, from precision agriculture to environmental science. A first step in the preparation of the algorithms to be employed outdoors starts at a laboratory level, capturing a high amount of samples to be analysed and processed in order to extract the necessary information about the spectral characteristics of the studied samples in the most precise way. In this article, a custom-made scanning system for hyperspectral image acquisition is described. Commercially available components have been carefully selected in order to be integrated into a flexible infrastructure able to obtain data from any Generic Interface for Cameras (GenICam) compliant devices using the gigabyte Ethernet interface. The entire setup has been tested using the Specim FX hyperspectral series (FX10 and FX17) and a Graphical User Interface (GUI) has been developed in order to control the individual components and visualise data. Morphological analysis, spectral response and optical aberration of these pushbroom-type hyperspectral cameras have been evaluated prior to the validation of the whole system with different plastic samples for which spectral signatures are extracted and compared with well-known spectral libraries.

The use of empirical agrometeorological models that can be adjusted to the climatic conditions of different regions has become increasingly necessary to improve water management in grain-producing municipalities. The aim of this work is to examine the correlation between various reference evapotranspiration (ETo) estimation methods and the standard FAO 56 Penman-Monteith method, as well as to determine correction factors, when necessary, for crop-producing municipalities in the northeast of Pará, during both the rainy and dry seasons. We compared simpler methods of ETo estimation to the FAO 56 Penman-Monteith method. For this purpose, meteorological data from Tracuateua, Bragança, Capitão Poço and Castanhal, provided by the National Institute of Meteorology (INMET), were used. The calibration of equations was performed through linear regression. The accuracy of different estimation methods was examined. The Turc, FAO 24 Blaney-Criddle and regression methods presented the best results for all statistical criteria; the Priestley-Taylor, Makkink and FAO 24 Radiation methods presented excellent results after calibration. The methods of Camargo and Hargreaves-Samani produced the worst results for all the criteria.

The primary treatment for malignant brain tumors is surgical resection. While gross total resection improves the prognosis, a supratotal resection may result in neurological deficits. On the other hand, accurate intraoperative identification of the tumor boundaries may be very difficult, resulting in subtotal resections. Histological examination of biopsies can be used repeatedly to help achieve gross total resection but this is not practically feasible due to the turn-around time of the tissue analysis. Therefore, intraoperative techniques to recognize tissue types are investigated to expedite the clinical workflow for tumor resection and improve outcome by aiding in the identification and removal of the malignant lesion. Hyperspectral imaging (HSI) is an optical imaging technique with the power of extracting additional information from the imaged tissue. Because HSI images cannot be visually assessed by human observers, we instead exploit artificial intelligence techniques and leverage a Convolutional Neural Network (CNN) to investigate the potential of HSI in twelve in vivo specimens. The proposed framework consists of a 3D–2D hybrid CNN-based approach to create a joint extraction of spectral and spatial information from hyperspectral images. A comparison study was conducted exploiting a 2D CNN, a 1D DNN and two conventional classification methods (SVM, and the SVM classifier combined with the 3D–2D hybrid CNN) to validate the proposed network. An overall accuracy of 80% was found when tumor, healthy tissue and blood vessels were classified, clearly outperforming the state-of-the-art approaches. These results can serve as a basis for brain tumor classification using HSI, and may open future avenues for image-guided neurosurgical applications.

Hyperspectral imaging is a multidimensional optical technique with the potential of providing fast and accurate tissue classification. The main challenge is the adequate processing of the multidimensional information usually linked to long processing times and significant computational costs, which require expensive hardware. In this study, we address the problem of tissue classification for intraoperative hyperspectral images of in vivo brain tissue. For this goal, two methodologies are introduced that rely on a blind linear unmixing (BLU) scheme for practical tissue classification. Both methodologies identify the characteristic end-members related to the studied tissue classes by BLU from a training dataset and classify the pixels by a minimum distance approach. The proposed methodologies are compared with a machine learning method based on a supervised support vector machine (SVM) classifier. The methodologies based on BLU achieve speedup factors of ~459× and ~429× compared to the SVM scheme, while keeping constant and even slightly improving the classification performance.

The combination of hyperspectral imaging (HSI) and digital pathology may yield more accurate diagnosis. In this work, we propose the use of superpixels in HS images for combining regions of pixels that can be classified according to their spectral information to classify glioblastoma (GB) brain tumors in histologic slides. The superpixels are generated by a modified simple linear iterative clustering (SLIC) method to accommodate HS images. This work employs a dataset of H&E (Hematoxylin and Eosin) stained histology slides from 13 patients with GB and over 426,000 superpixels. A linear support vector machine (SVM) classifier was performed on independent training, validation, and testing datasets. The results of this investigation show that the proposed method can detect GB brain tumors from non-tumor samples with average sensitivity and specificity of 87% and 81%, respectively. The overall accuracy of this method is 83%. The study demonstrates that hyperspectral digital pathology can be useful for detecting GB brain tumors by exploiting spectral information alone on a superpixel level.

The midday stem water potential (Ψs) and stomatal conductance (gs) have been traditionally used to monitor the water status of cherry trees (Prunus avium L.). Due to the complexity of direct measurement, the use of infrared thermography has been proposed as an alternative. This study compares Ψs and gs against crop water stress indexes (CWSI) calculated from thermal infrared (TIR) data from high-resolution (HR) and low-resolution (LR) cameras for two cherry tree cultivars: ‘Regina’ and ‘Sweetheart’. For this purpose, a water stress–recovery cycle experiment was carried out at the post-harvest period in a commercial drip-irrigated cherry tree orchard under three irrigation treatments based on Ψs levels. The water status of trees was measured weekly using Ψs, gs, and compared to CWSIs, computed from both thermal cameras. Results showed that the accuracy in the estimation of CWSIs was not statistically significant when comparing both cameras for the representation of Ψs and gs in both cultivars. The performance of all evaluated physiological indicators presented similar trends for both cultivars, and the averaged differences between CWSI’s from both cameras were 11 ± 0.27%. However, these CWSI’s were not able to detect differences among irrigation treatments as compared to Ψs and gs.

Given an object of interest that evolves in time, one often wants to detect possible changes in its properties. The first changes may be small and occur in different scales and it may be crucial to detect them as early as possible. Examples include identification of potentially malignant changes in skin moles or the gradual onset of food quality deterioration. Statistical scale-space methodologies can be very useful in such situations since exploring the measurements in multiple resolutions can help identify even subtle changes. We extend a recently proposed scale-space methodology to a technique that successfully detects such small changes and at the same time keeps false alarms at a very low level. The potential of the novel methodology is first demonstrated with hyperspectral skin mole data artificially distorted to include a very small change. Our real data application considers hyperspectral images used for food quality detection. In these experiments the performance of the proposed method is either superior or on par with a standard approach such as principal component analysis.

Hyperspectral imaging (HSI) technology has demonstrated potential to provide useful information about the chemical composition of tissue and its morphological features in a single image modality. Deep learning (DL) techniques have demonstrated the ability of automatic feature extraction from data for a successful classification. In this study, we exploit HSI and DL for the automatic differentiation of glioblastoma (GB) and non-tumor tissue on hematoxylin and eosin (H&E) stained histological slides of human brain tissue. GB detection is a challenging application, showing high heterogeneity in the cellular morphology across different patients. We employed an HSI microscope, with a spectral range from 400 to 1000 nm, to collect 517 HS cubes from 13 GB patients using 20× magnification. Using a convolutional neural network (CNN), we were able to automatically detect GB within the pathological slides, achieving average sensitivity and specificity values of 88% and 77%, respectively, representing an improvement of 7% and 8% respectively, as compared to the results obtained using RGB (red, green, and blue) images. This study demonstrates that the combination of hyperspectral microscopic imaging and deep learning is a promising tool for future computational pathologies.

In the Chilean viticultural industry, Carménère is considered an emblematic cultivar that is cultivated mainly in arid and semi-arid zones. For this reason, it is necessary to use precise irrigation scheduling for improving water use efficiency (WUE), water productivity (WP), yield and wine quality. This study evaluated the effects of three deficit irrigation strategies on gas exchange variables, WUE, WP and yield components in a drip-irrigated Carménère vineyard growing under semi-arid climatic conditions during two consecutive seasons (2011/12 and 2012/13). The irrigation strategies were applied in completely randomized design from fruit set (S) to harvest (H). The first irrigation strategy (T1) involved continuous irrigation at 100% of actual evapotranspiration (ETa) from S to the veraison (V) period and at 80% of ETa from V to H. The second irrigation strategy (T2) involved irrigation at 50% of ETa from S to H and the third one (T3) involved no-irrigation from S to V and at 30% of ETa from V to H. The results indicated that there was a significant non-linear correlation between net CO2 assimilation (AN) and stomatal conductance (gs), which resulted in three zones of water stress (zone I = gs > 0.30 mol H2O m-2s-1; zone II = between 0.06 and 0.30 mol H2O m-2s-1; and zone III = gs < 0.06 mol H2O m-2s-1). The use of less water by T2 and T3 had a significant effect on yield components, with a reduction in the weight and diameter of grapes. A significant increase in WP (7.3 kg m-3) occurred in T3, which resulted in values of WUE that were significantly higher than those from T1 and T2. Also, a significant non-linear relationship between the integral water stress (SIΨ) and WP (R2 = 0.74) was established. The results show that grafted Carménère vines were tolerant to water stress although differences between cultivars/genotypes still need to be evaluated.

Surgery for brain cancer is a major problem in neurosurgery. The diffuse infiltration into the surrounding normal brain by these tumors makes their accurate identification by the naked eye difficult. Since surgery is the common treatment for brain cancer, an accurate radical resection of the tumor leads to improved survival rates for patients. However, the identification of the tumor boundaries during surgery is challenging. Hyperspectral imaging is a non-contact, non-ionizing and non-invasive technique suitable for medical diagnosis. This study presents the development of a novel classification method taking into account the spatial and spectral characteristics of the hyperspectral images to help neurosurgeons to accurately determine the tumor boundaries in surgical-time during the resection, avoiding excessive excision of normal tissue or unintentionally leaving residual tumor. The algorithm proposed in this study to approach an efficient solution consists of a hybrid framework that combines both supervised and unsupervised machine learning methods. Firstly, a supervised pixel-wise classification using a Support Vector Machine classifier is performed. The generated classification map is spatially homogenized using a one-band representation of the HS cube, employing the Fixed Reference t-Stochastic Neighbors Embedding dimensional reduction algorithm, and performing a K-Nearest Neighbors filtering. The information generated by the supervised stage is combined with a segmentation map obtained via unsupervised clustering employing a Hierarchical K-Means algorithm. The fusion is performed using a majority voting approach that associates each cluster with a certain class. To evaluate the proposed approach, five hyperspectral images of surface of the brain affected by glioblastoma tumor in vivo from five different patients have been used. The final classification maps obtained have been analyzed and validated by specialists. These preliminary results are promising, obtaining an accurate delineation of the tumor area.

Leaf area index (LAI) is one of the key biophysical variables required for crop modeling. Direct LAI measurements are time consuming and difficult to obtain for experimental and commercial fruit orchards. Devices used to estimate LAI have shown considerable errors when compared to ground-truth or destructive measurements, requiring tedious site-specific calibrations. The objective of this study was to test the performance of a modified digital cover photography method to estimate LAI in apple trees using conventional digital photography and instantaneous measurements of incident radiation (Io) and transmitted radiation (I) through the canopy. Leaf area of 40 single apple trees were measured destructively to obtain real leaf area index (LAID), which was compared with LAI estimated by the proposed digital photography method (LAIM). Results showed that the LAIM was able to estimate LAID with an error of 25% using a constant light extinction coefficient (k = 0.68). However, when k was estimated using an exponential function based on the fraction of foliage cover (ff) derived from images, the error was reduced to 18%. Furthermore, when measurements of light intercepted by the canopy (Ic) were used as a proxy value for k, the method presented an error of only 9%. These results have shown that by using a proxy k value, estimated by Ic, helped to increase accuracy of LAI estimates using digital cover images for apple trees with different canopy sizes and under field conditions.

Phenological models have been made mainly for winegrape cultivars, despite the economic importance of table grapes. The aim of this work was to develop and validate models for predicting phenological scales of table grapes (cvs. Thompson, Crimson and Superior Seedless and Red Globe) grown under semi-arid conditions. Measurements of phenology were carried out weekly from budburst to harvest during four growing seasons (2009-2013). Phenology models were developed using the Mitscherlich monomolecular equation where the dependent and independent variables were the Eichhorn and Lorenz phenological (ELP) scale modified by Coombe and the growing degree days (GDD), respectively. Results indicated that there were strong non-linear correlations between the ELP scale and GDD for the four cultivars with coefficient of determinations (R2) ranging between 0.97-0.99. Also, validation indicated that the models were able to predict ELP scale with a root mean square (RMSE) and mean absolute error (MAE) ranging between 2.1-2.4 and 1.35-1.69, respectively. The prediction variability (expressed in days) was between 4.4-19.4 days, obtaining the best results for the flowering period. This study suggested that the phenological models based on GDD could be useful planning tools for farming, especially from budburst to veraison of table grape cultivars.

An increase in the land area dedicated to super-high density olive orchards has occurred in Chile in recent years. Such modern orchards have high irrigation requirements, and optimizing water use is a priority. Moreover, this region presents low water availability, which makes necessary to establish irrigation strategies to improve water productivity. An experiment was conducted during four consecutive growing seasons (2010–2011 to 2013–2014) to evaluate the responses of yield and water productivity to irrigation cut-off strategies. These strategies were applied after fruit set using midday stem water potential (Ψstem) thresholds in a super-high density olive orchard (cv. Arbequina), located in the Pencahue Valley, Maule Region, Chile. The experimental design was completely randomized with four irrigation cut-off treatments based on the Ψstem thresholds and four replicate plots per treatment (five trees per plot). Similar to commercial growing conditions in our region, the Ψstem in the T1 treatment was maintained between -1.4 and -2.2 MPa (100% of actual evapotranspiration), while T2, T3 and T4 treatments did not receive irrigation from fruit set until they reached a Ψstem threshold of approximately -3.5, -5.0, and -6.0 MPa, respectively. Once the specific thresholds were reached, irrigation was restored and maintained as T1 in all treatments until fruits were harvested. Yield and its components were not significantly different between T1 and T2, but fruit yield and total oil yield, fruit weight, and fruit diameter were decreased by the T3 and T4 treatments. Moreover, yield showed a linear response with water stress integral (SΨ), which was strongly influenced by fruit load. Total oil content (%) and pulp/stone ratio were not affected by the different irrigation strategies. Also, fruit and oil water productivities were significantly greater in T1 and T2 than in the T3 and T4. Moreover, the T2, T3, and T4 treatments averaged 37, 51, and 72 days without irrigation which represented 75–83, 62–76, and 56–70% of applied water compared with T1, respectively. These results suggest that using the T2 irrigation cut-off strategy could be applied in a super-high density olive orchard (cv. Arbequina) because it maintained yields, saving 20% of the applied water.

A study was carried out to parameterize the METRIC (Mapping EvapoTranspiration at high Resolution with Internalized Calibration) model for estimating instantaneous values of albedo (shortwave albedo) (αi), net radiation (Rni) and soil heat flux (Gi), sensible (Hi) and latent heat (LEi) over a drip-irrigated Merlot vineyard (location: 35°25′ LS; 71°32′ LW; 125 m.a.s. (l). The experiment was carried out in a plot of 4.25 ha, processing 15 Landsat images, which were acquired from 2006 to 2009. An automatic weather station was placed inside the experimental plot to measure αi, Rni and Gi. In the same tower an Eddy Covariance (EC) system was mounted to measure Hi and LEi. Specific sub-models to estimate Gi, leaf area index (LAI) and aerodynamic roughness length for momentum transfer (zom) were calibrated for the Merlot vineyard as an improvement to the original METRIC model. Results indicated that LAI, zom and Gi were estimated using the calibrated functions with errors of 4%, 2% and 17%, while those were computed using the original functions with errors of 58%, 81%, and 5%, respectively. At the time of satellite overpass, comparisons between measured and estimated values indicated that METRIC overestimated αi in 21% and Rni in 11%. Also, METRIC using the calibrated functions overestimated Hi and LEi with errors of 16% and 17%, respectively while it using the original functions overestimated Hi and LEi with errors of 13% and 15%, respectively. Finally, LEi was estimated with root mean square error (RMSE) between 43 and 60 W∙m−2 and mean absolute error (MAE) between 35 and 48 W∙m−2 for both calibrated and original functions, respectively. These results suggested that biases observed for instantaneous pixel-by-pixel values of Rni, Gi and other intermediate components of the algorithm were presumably absorbed into the computation of sensible heat flux as a result of the internal self-calibration of METRIC.

The main goal of brain cancer surgery is to perform an accurate resection of the tumor, preserving as much normal brain tissue as possible for the patient. The development of a non-contact and label-free method to provide reliable support for tumor resection in real-time during neurosurgical procedures is a current clinical need. Hyperspectral imaging is a non-contact, non-ionizing, and label-free imaging modality that can assist surgeons during this challenging task without using any contrast agent. In this work, we present a deep learning-based framework for processing hyperspectral images of in vivo human brain tissue. The proposed framework was evaluated by our human image database, which includes 26 in vivo hyperspectral cubes from 16 different patients, among which 258,810 pixels were labeled. The proposed framework is able to generate a thematic map where the parenchymal area of the brain is delineated and the location of the tumor is identified, providing guidance to the operating surgeon for a successful and precise tumor resection. The deep learning pipeline achieves an overall accuracy of 80% for multiclass classification, improving the results obtained with traditional support vector machine (SVM)-based approaches. In addition, an aid visualization system is presented, where the final thematic map can be adjusted by the operating surgeon to find the optimal classification threshold for the current situation during the surgical procedure.

The work presented in this paper is focused on the use of spectroscopy to identify the type of tissue of human brain samples employing support vector machine classifiers. Two different spectrometers were used to acquire infrared spectroscopic signatures in the wavenumber range between 1200⁻3500 cm−1. An extensive analysis was performed to find the optimal configuration for a support vector machine classifier and determine the most relevant regions of the spectra for this particular application. The results demonstrate that the developed algorithm is robust enough to classify the infrared spectroscopic data of human brain tissue at three different discrimination levels.

The use of hyperspectral imaging (HSI) in the medical field is an emerging approach to assist physicians in diagnostic or surgical guidance tasks. However, HSI data processing involves very high computational requirements due to the huge amount of information captured by the sensors. One of the stages with higher computational load is the K-Nearest Neighbors (KNN) filtering algorithm. The main goal of this study is to optimize and parallelize the KNN algorithm by exploiting the GPU technology to obtain real-time processing during brain cancer surgical procedures. This parallel version of the KNN performs the neighbor filtering of a classification map (obtained from a supervised classifier), evaluating the different classes simultaneously. The undertaken optimizations and the computational capabilities of the GPU device throw a speedup up to 66.18× when compared to a sequential implementation.

A study was carried out to evaluate the potential use of the two-source Shuttleworth and Wallace (SW) model to compute the intra-orchard spatial variability of actual evapotranspiration (ET) of olive trees using satellite images and ground-based climate data. The study was conducted in a drip-irrigated olive orchard using satellite images (Landsat 7 ETM+), which were acquired on clear sky days during the main phenological stages (2009/10 growing season). The performance of the SW model was evaluated using instantaneous latent heat flux (LE) measurements that were obtained from an eddy correlation system. At the time of satellite overpass, the estimated values of net radiation ( Rn i ) and soil heat flux ( G i ) were compared with ground measurements from a four-way net radiometer and soil heat flux plates, respectively. The results indicated that the SW model subestimated instantaneous LE (W m−2) and daily ET (mm d−1), with errors of 12% and 10% of observed values, respectively. The root mean square error (RMSE) and mean absolute error (MAE) values for instantaneous LE were 26 and 20 W m−2, while those for daily values of ET were 0.31 and 0.28 mm d−1, respectively. Finally, the submodels computed Rn i and G i with errors of between 4.0% and 8.0% of measured values and with RMSE and MAE between 25 and 39 W m−2.