Search Results (43)

The internal quality assessment of potato tubers is a crucial task in agro-laboratory processing. Traditional methods struggle to detect internal defects such as hollow heart, internal bruises, and insect galleries using only surface features. We present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices, suitable for integration in laboratory. Our pipeline combines high-recall multi-threshold YOLO detection, contextual patch validation using ResNet, precise segmentation via the Segment Anything Model (SAM), and skin-contact analysis using VGG16 with a Random Forest classifier. Experimental results on a labeled dataset of over 6000 annotated instances show a recall above 95% and precision near 97.2% for most defect classes. The approach offers both robustness and interpretability, outperforming previous methods that rely on costly hyperspectral or MRI techniques. This system is scalable, explainable, and compatible with existing 2D imaging hardware. Full article

The classification of cork planks as a raw material is traditionally performed through visual inspection of cork pores and defects, both in forest owners’ associations and industrial settings. This method introduces subjectivity and limits reproducibility. This study aimed to develop near-infrared spectroscopy (NIRS) models for predicting porosity in raw cork, distinguishing virgin, secondary, and mature cork types. A total of 156 cork samples representing the three cork types were analyzed. Spectra were collected on the transverse and radial surfaces using a Bruker MPA spectrophotometer. Partial Least Squares Regression (PLS-R) models were developed separately for each cork type, yielding cross-validated coefficients of determination (R²) between 0.48 and 0.64. Additionally, two global models were obtained using a random data split (60% for cross-validation and 40% for validation), differentiated by whether or not areas corresponding to insect galleries were included. The model incorporating insect galleries achieved R² values of 0.63 (cross-validation) and 0.46 (validation), while the model excluding them yielded R² values of 0.51 and 0.52, respectively. The final optimized model, based on all samples and using selected spectral regions (9500–7500 and 6100–5450 cm⁻¹) with first derivative and vector normalization preprocessing, achieved an R² of 0.61, RMSECV of 0.025, and RPD of 1.6 using five latent variables. This model was used to estimate porosity coefficients in visually classified secondary and mature cork. Results confirmed an inverse relationship between porosity and cork quality class: higher-quality classes (Q1, Q2) had lower porosity, with Q1 being the most homogeneous. Porosity increased from Q2 to Q6 in mature cork, expressing declining quality. Greater variability in lower-quality classes highlights porosity’s relevance for classification. These results demonstrate the potential of NIRS as a non-destructive tool for assessing cork porosity, offering a more objective and efficient alternative to conventional methods. Full article

Fungi and bacteria associated with bark beetles can facilitate successful tree colonization, and, in some cases, these fungi act as pathogens of trees. The red turpentine beetle (RTB, Dendroctonus valens) is a bark beetle native to North America that colonizes stressed pines, rarely killing healthy trees. The fungal communities associated with RTB adults, larval galleries, and control tree phloem from red pine (Pinus resinosa) and white pine (P. strobus) forests in the Great Lakes region of the United States were characterized using both culture-independent and culture-dependent methods. Similarly, the bacterial communities associated with RTB adults in the same region were characterized using a culture-independent method. There were significant differences between the adult beetle fungal communities and the tree-based fungal communities. Culture-independent sequencing of RTB adults showed high abundances of the fungal order Filobasidiales (red pine: 28.71% relative abundance, white pine: 6.91% relative abundance), as well as the bacterial orders Enterobacterales (red pine: 53.72%, white pine: 22.15%) and Pseudomonadales (red pine: 15.86%, white pine: 12.91%). In contrast, we isolated high amounts of fungi in the orders Pleosporales (red pine: 21.79%, white pine: 15.90%) and Eurotiales (red pine: 15.38%, white pine: 16.51%) from the adult beetles by culturing. Culture-independent sequencing of beetle galleries yielded high abundances of fungi in the orders Helotiales (red pine: 22.23%, white pine: 23.21%), whereas culture-based isolation from the same galleries yielded high amounts of Eurotiales (red pine: 17.91%, white pine: 17.91%), Hypocreales (red pine: 16.42%, white pine: 16.42%), and Ophiostomatales (red pine: 23.39%, white pine: 23.39%). This contrasts with the culture-independent method, where, likely due to limitations in the sequencing method, the Ophiostomatales accounted for only around 2% of the fungi from RTB galleries in both pine species. We observed a high species-level diversity of Ophiostomatales associated with RTB, isolating 14 species from the Great Lakes region. Leptographium terebrantis, a species that has been described in association with RTB throughout the United States, was the most common species (e.g., >35% of the Ophiostomatales relative abundance in red pine environments and >14% of the Ophiostomatales relative abundance in the white pine environment). This study enhances our understanding of RTB-associated fungi and bacteria in the beetle’s native range at both the community and species levels. Full article

Progressive climate change has increased the emergence of bark beetle outbreaks, which justifies the need for in-depth research into their response to climatic factors in order to improve forest resource management strategies. A measure of the adaptation of species to changing conditions is provided by the determination of the breadth of their ecological niches. This study proposes a novel, minimally invasive method to estimate the niche breadth of Tomicus piniperda, a representative species in its taxonomic group. EntomologiJcal analyses were carried out on trap trees. The niche of T. piniperda was described by means of stepwise regression, and its niche breadth was found to depend significantly on the bark thickness and gallery density on stems (p < 0.001). The constructed models explained over 80% of the variation in T. piniperda niche breadth on the stems, and the differences between the observed and predicted mean niche breadth were not significant (p > 0.05), with the relative errors for individual trees generally not exceeding 13%. Data on the parameters of niches may be useful in evaluating the possible consequences of changes in climatic factors for organismal fitness, for example, or as a starting point for the construction of models of bark beetle population size. Full article

The Cerrado domain, one of the richest on Earth, is among the most threatened in South America due to human activities, resulting in biodiversity loss, altered fire dynamics, water pollution, and other environmental impacts. Monitoring this domain is crucial for preserving its biodiversity and ecosystem services. This study aimed to apply machine learning techniques to classify the main vegetation formations of the Cerrado within the IBGE Ecological Reserve, a protected area in Brazil, using high-resolution PlanetScope imagery from 2021 to 2024. Three machine learning methods were evaluated: Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). A post-processing process was applied to avoid misclassification of forest in areas of savanna. After performance evaluation, the SVM method achieved the highest classification accuracy (overall accuracy of 97.51%, kappa coefficient of 0.9649) among the evaluated models. This study identified five main classes: grassland (GRA), savanna (SAV), bare soil (BS), samambaião (SAM, representing the superdominant species Pteridium esculentum), and forest (FOR). Over the three-year period (2021–2024), SAV and GRA formations were dominant in the reserve, reflecting the typical physiognomies of the Cerrado. This study successfully delineated areas occupied by the superdominant species P. esculentum, which was concentrated near gallery forests. The generated maps provide valuable insights into the vegetation dynamics within a protected area, aiding in monitoring efforts and suggesting potential new areas for protection in light of imminent anthropogenic threats. This study demonstrates the effectiveness of combining high-resolution satellite imagery with machine learning techniques for detailed vegetation mapping and monitoring in the Cerrado domain. Full article

The juniper (Taxodium mucronatum Ten. of the Cupressaceae family) is a long-lived species that forms gallery forests. Dozens of dead junipers > 100 years old have been identified in the San Pedro Mezquital watershed in Durango, Mexico. This work determines the causes of death of these specimens. The work was carried out in the field and in the laboratory, where in the former the surface of the damaged trees was identified, together with the changes observed in the watercourses. In the latter, sabino seedlings were transported to the work center and exposed for 7 days in containers with gravel to five types of wastewater generated in the region. With the above, the conditions experienced by the adult trees in the field were studied, as well as the sensitivity of the young specimens to the types of water quality, and the differences were validated with ANOVA tests. Five sites with dead junipers were found, ranging in size from 0.5 to 4 ha, with ages between 200 and 400 years. It was found that during the dry season, water is diverted to irrigated areas, leaving some areas without water for several months. The shoots survived in most of the water qualities, except the one with high salinity (3.34 mS/cm). It is concluded that the lack of water in the rivers had a stronger influence than the water quality and is the probable cause of the death of the sabino. Full article

The Cerrado has high plant and vertebrate diversity and is an important biome for conserving species and provisioning ecosystem services. Volume equations in this biome are scarce because of their size and physiognomic diversity. This study was conducted to develop specific volumetric models for the phytophysiognomies Gallery Forest, Dry Forest, Forest Savannah, and Savannah Woodland, a generic model and a model for Cerrado forest formation. Twelve 10 m × 10 m (100 m²) (National Forest Inventory) plots were used for each phytophysiognomy at different sites (regions) of the Federal District (FD) where trees had a diameter at breast height (DBH; 1.30 m) ≥5 cm in forest formations and a diameter at base height (Db; 0.30 m) ≥5 cm in savanna formations. Their diameters and heights were measured, they were cut and cubed, and the volume of each tree was obtained according to the Smalian methodology. Linear and nonlinear models were adjusted. Criteria for the selection of models were determined using correlation coefficients, the standard error of the estimates, and a graphical analysis of the residues. They were later validated by the chi-square test. The resultant models indicated that fit by specific phytophysiognomy was ideal; however, the generic and forest formation models exhibited similar performance to specific models and could be used in extensive areas of the Cerrado, where they represent a high potential for generalization. To further increase our understanding, similar research is recommended for the development of specific and generic models of the total volume in Cerrado areas. Full article

Epiphytes represent a key component in tropical forests. They are affected by anthropogenic and natural disturbances suffered by forests, since they depend on their hosts and the microclimatic conditions they generate. We analyzed differences in abundance, species richness, and vertical distributions of epiphytic bromeliads in primary and disturbed forests. We found a higher abundance (5316 individuals) and species richness (8 species) of bromeliads in disturbed forest than in primary forest (1360 individuals and 4 species, respectively). Most bromeliads (97%) were found on Taxodium mucronatum, a dominant tree with rough bark in the disturbed forest (gallery forest). Bromeliads were more abundant in the middle of the tree and diminished towards the trunk base and the upper crown. Tillandsia baileyi was the most abundant bromeliad, and the size categories of this species differentially colonize trees in gallery forest according to Johansson zones; seedlings of T. baileyi abundantly colonize the upper canopy, and juveniles colonize the middle canopy or secondary branches. Gallery forest represents an important reservoir for epiphytic bromeliads. Hence, it is important to extend this kind of study to wetland sites to understand the role they play as a habitat for epiphytes, as well as the dynamics and ecological processes that occur in such habitats. Full article

Climate and land cover changes are key factors in river basins’ management. This study investigates on the one hand 60-year (1960 to 2019) rainfall and temperature variability using station data combined with gridded data, and on the other hand land cover changes for the years 1990, 2005, and 2020 in the Sota catchment (13,410 km², North Benin, West Africa). The climate period is different from the chosen land use change period due to the unavailability of satellite images. Standardized anomaly index, break points, trend analysis, and Thiessen’s polygon were applied. Satellite images were processed and ground truthing was carried out to assess land cover changes. The analyses revealed a wet period from 1960 to 1972, a dry period from 1973 to 1987, and another wet period from 1988 to 2019. The annual rainfall decreases from the south to the north of the catchment. In addition, rainfall showed a non-significant trend over the study period, and no significant changes were identified between the two normals (1960–1989 and 1990–2019) at catchment scale, although some individual stations exhibited significant trends. Temperatures, in contrast, showed a significant increasing trend over the study period at catchment scale, with significant break points in 1978, 1990, and 2004 for Tmax, and 1989 for Tmin. An increase of 0.4 °C and 1.2 °C is noted, respectively, for Tmax and Tmin between the two normals. The study also revealed increases in agricultural areas (212.1%), settlements (76.6%), waterbodies (2.9%), and baresoil (52%) against decreases in woodland (49.6%), dense forest (42.2%), gallery forest (21.2%), and savanna (31.9%) from 1990 to 2020. These changes in climate and land cover will have implications for the region. Appropriate adaptation measures, including Integrated Water Resources Management and afforestation, are required. Full article

The Niokolo Koba National Park (NKNP) is the largest protected area in Senegal and lies at the northern limit of the chimpanzee’s range in West Africa. Recent information on nesting behavior and factors influencing nesting behavior is available for several sites outside NKNP. However, the information available for NKNP is obsolete. Considering that the adequate management of chimpanzee populations cannot be achieved without strong scientific knowledge, it is essential to update data on chimpanzee, Pan troglodytes verus, nesting behavior in NKNP. For this reason, we surveyed their habitat in Mt. Assirik and recorded 626 chimpanzee nests. The results of the study showed that chimpanzees nest more often in closed-canopy habitats such as gallery forests. The average nest height observed in this study was 8.07 ± 0.36 m, varying between 2 and 20 m, which is well below the heights described in most sites where chimpanzees cohabit with large carnivores. Botanical surveys confirmed that chimpanzees select tree species bearing their nests. In Assirik, 12 of the 37 tree species bearing nests are the most used. The nest decay rate (or the time it takes for a nest to go from the fresh to the skeletal stage) at Assirik averaged 68.8 ± 5.8 days. Full article

In recent decades, there has been a perception that the Mozambican forests have been threatened with massive exploitation for commercialization, deforesting vast areas, leading to desertification and contributing to the extinction of some forest species. The present research summarizes the official information obtained by monitoring the country’s natural resources over time and identifying the major types of existing forests in Mozambique. The main objective is to elucidate on the current state of Mozambican forests, analyze change and trends, and characterize the actual distribution of forest species in Mozambique to verify the sustainability of forest resources and their composition. It is a case study of the qualitative descriptive type, with data obtained through a bibliographic research method focusing on scientific articles on the type of forest species existing in Africa and Mozambique and data from official sources of the forests. Various types of forests were identified, such as mopane, mercrusse, semi-deciduous, miombo, and semi-evergreen, including the gallery forest. Forest species with particular relevance were highlighted, such as Afzelia quanzensis, Swartzia madagascariensis, Pterocarpaus angolensis, Combretum imberbe, and Millettia stuhalmannii. Major threats to these natural resources were identified and reported, including anthropogenic activity associated with traditional practices of illegal logging or due to the valuation of other goods of primary necessity, lack of protection and conservation measures, and impacts resulting from climate change. The Munza district is presented as a case study, carrying out a characterization of the forest in this district and identifying the main threats in the study area from 2015 to 2020. Full article

Deforestation is an important environmental problem and a key promoter of regional climate change through modifying the surface albedo. The objective of this research was to characterize the impact of deforestation and land use changes on surface albedo (α) and climate patterns in a tropical highland region of Mexico, between the years 2014 and 2021. The main land cover types are coniferous forests (CF), oak and gallery woodlands (OGW), and annual agriculture (AA), which represent more than 88% of the regional territory. We used 2014 and 2021 Landsat 8 OLI images with topographic and atmospheric correction in order to develop an inventory of albedo values for each land cover type in both time scenarios. Albedo images were generated by using the equation proposed by Liang in 2001, which is based on the reflectance of the bands 2, 3, 4, 5, and 7. Differences in albedo values were calculated between the years 2014 and 2021, and those differences were correlated with variations in climate parameters, for which we used climate data derived from the WRF model. In addition, the different land use changes found were classified in terms of triggers for increasing or decreasing surface albedo. We used the Mann–Whitney U Test to compare the 2021 − 2014 climatic deviations in two samples: Sample A, which included sites without albedo change in 2021; and Sample B, including sites with albedo change in 2021. Results showed that between 2014 and 2021, at least 38 events of land use change or deforestation occurred, with albedo increments between 1 and 11%, which triggered an average increment of 2.16% (p < 0.01; Mann–Whitney U Test) of the regional surface albedo in comparison to the 2014 scenario. In this period, the albedo for CF, OGW, and AA also increased significantly (p < 0.001; Mann–Whitney U Test) by +79, +12, and +9%, respectively. In addition, the regional albedo increment was found to be significant and negatively correlated (p < 0.01 Spearman’s coefficient) with relative humidity (RH), maximum temperature (Tmax), and minimum temperature (Tmin), and correlated (p < 0.01) positively with diurnal temperature range (DTR). The Mann–Whitney U Test revealed that 2021 climatic variations in Sample B sites are statistically different (p < 0.05) to 2021 climatic variations in Sample A sites, which demonstrates that albedo changes are linked to a decrease in minimum temperature and relative humidity and an increase in DTR. Conversion of CF and OGW into AA, perennial agriculture (PA), or grassland (GR) always yielded an albedo increment, whilst the conversion of AA to irrigation agriculture (IA) or PA triggered a decrease in albedo, and finally, the pass from GR or AA to protected agriculture (PA) caused albedo to increase or decrease, depending on the greenhouse covers materials. Reducing deforestation of CF and OGW, conversion of AA or GR into PA, and selecting adequate greenhouse covers could help to mitigate regional climate change. Full article

Affem Boussou community forest (AFC) abounds in important biological resources. This study, which contributes to its better management, examines the spatiotemporal dynamics of the vegetation and its ecological and structural characteristics to propose a zoning plan for said forest. The analysis of the spatiotemporal dynamics of land use in the AFC from Google Earth images of 2015, 2018, and 2021 revealed a regressive trend of formations: crops and fallows (−33.98%), dense dry forests (−7.92%), gallery forests (−3.46%), plantations (−100%), grassy savannahs, and meadows (−18.84%), except for tree/shrub savannahs (484.23%). The floristic inventory identified 163 species divided into 129 genera and 55 families. Fabaceae (14.02%), and Combretaceae (10.55%) are the most represented families. Anogeissus leiocarpa (5.19%) and Vitellaria paradoxa (4.72%) are the most frequent species. We note the dominance of individuals of small diameters. The regeneration potential of the AFC is 64 feet/ha due to 21 feet/ha of suckers, 29 feet/ha of seedlings, and 14 feet/ha of shoots. As a zoning plan, the AFC was subdivided into four zones: the agroforestry zone (18.80%), the sustainable production forest zone (42.22%), the buffer zone (11%), and the biological conservation zone (28%). These results constitute a scientific basis for testing ecological indicators of the sustainable management of community forests in Togo. Full article

The mountain pine beetle, Dendroctonus ponderosae Hopkins (Coleoptera: Curculionidae), recently underwent a notable range-expansion event in western Canada, resulting in access to the novel host jack pine, Pinus banksiana Lamb. We assessed the suitability of jack pine for mountain pine beetle, as well as the historic host lodgepole pine, Pinus contorta Dougl. var. latifolia Engelm., and the non-Pinus host white spruce, Picea glauca (Moench) Voss, to help inform an assessment of the risk of future spread into Canada’s boreal forest and to further our understanding of host use in bark beetles. Several performance traits we measured were similar between lodgepole pine and jack pine, but gallery length and productivity indicated that lodgepole pine was the more suitable host. Development appeared to be faster in jack pine; however, in contrast to previous studies, we attribute it to oviposition arresting earlier in the novel host compared to the other hosts and not a difference in development rate. Initial productivity was surprisingly high in spruce, but we found evidence of a delayed negative effect that manifested as reduced cold tolerance, delayed development, and high mortality of late-instar larvae. Although jack pine is a suitable host for the mountain pine beetle, our results indicate that the beetle’s eruptive potential could be lower in jack pine compared to lodgepole pine, given all other factors are equal. Other factors that may also affect mountain pine beetle population dynamics require additional research and include the composition and structure of jack pine forests, environmental conditions, and biotic interactions. Full article

The vegetation cover of the Ouémé Delta constitutes a biodiversity hotspot for the wetlands in southern Benin. However, the overexploitation of natural resources in addition to the intensification of agricultural practices led to the degradation of the natural ecosystems in this region. The present work aims to reconstruct, using remote sensing, the spatial dynamics of land use in the Ouémé Delta in order to assess the recent changes and predict the trends in its vegetation cover. The methodology was based on remote sensing and GIS techniques. Altogether, this process helped us carry out the classification of Landsat images for a period of 30 years (stating year 1990, 2005, and 2020) via the Envi software. The spatial statistics resulting from this processing were combined using ArcGIS software to establish the transition matrices in order to monitor the conversion rates of the land cover classes obtained. Then, the prediction of the plant landscape by the year 2035 was performed using the “Land Change Modeler” extension available under IDRISI. The results showed seven (07) classes of occupation and land use. There were agglomerations, mosaics of fields and fallow land, water bodies, dense forests, gallery forests, swamp forests, and shrubby wooded savannahs. The observation of the vegetation cover over the period of 15 years from 1990 to 2005 showed a decrease from 71.55% to 63.42% in the surface area of the Ouémé Delta. A similar trend was noticed from 2005 to 2020 when it reached 55.19%, entailing a loss of 16.37% of the surface area of natural habitats in 30 years. The two drivers of such changes are the fertility of alluvial soils for agriculture along and urbanization. The predictive modeling developed for 2035 reveals a slight increase in the area of dense forests and shrubby wooded savannas, contrary to the lack of significant decrease in the area of gallery forests and swamp forests. This is key information that is expected to be useful to both policy and decision makers involved in the sustainable management and conservation of natural resources in the study area. Full article