1,720,965 research outputs found
Laying the foundation for an artificial neural network for photogrammetric riverine bathymetry
Full text linkThis work aims to test the effectiveness of artificial intelligence for correcting water refraction in shallow inland water using very high-resolution images collected by Unmanned Aerial Systems (UAS) and processed through a total FOSS workflow. The tests focus on using synthetic information extracted from the visible component of the electromagnetic spectrum. An artificial neural network is created using data of three morphologically similar alpine rivers. The RGB information, the SfM depth and seven radiometric indices are calculated and stacked in an 11-bands raster (input dataset). The depths are calculated as the difference between the Up component of the bathymetry cross-sections and the water surface quotas and constitute the dependent variable of the regression. The dataset is then scaled. The observations of one of the analyzed case studies are used as the unseen dataset to test the generalization capability of the model. The remaining observations are divided into test (20%) and training (80%) datasets. The generated NN is a 3-layer MLP model with one hidden layer and the Rectified Linear Unit (ReLU) and sigmoid activation functions. The weights are initialized to small Gaussian random values, and kernel regularizers, L1 and L2, are added to reduce the overfitting. Weights are updated with the Adam search technique, and the mean squared error is the loss function. The importance and significance of 11 variables are assessed. The model has a 0.70 r-squared score on the test dataset and 0.77 on the training dataset. The MAE is 0.06 and the RMSE 0.08, similar results obtained from the unseen dataset. Although the good metrics, the model shows some difficulties generalizing swallow depths
Riparian ecosystems mapping at fine scale: a density approach based on multi-temporal UAV photogrammetric point clouds
Get PDFIn recent years, numerous directives worldwide have addressed the conservation and restoration of riparian corridors, activities that rely on continuous vegetation mapping to understand its volumetric features and health status. Mapping riparian corridors requires not only fine-scale resolution but also the coverage of relatively large areas. The use of Unmanned Aerial Vehicles (UAV) allows for meeting both conditions, although the cost-effectiveness of their use is highly influenced by the type of sensor mounted on them. Few works have so far investigated the use of photogrammetric sensors for individual tree crown detection, despite being cheaper than the most common Light Detection and Ranging (LiDAR) ones. This work aims to improve the individual crown detection from UAV-photogrammetric datasets in a twofold way. Firstly, the effectiveness of a new approach that has already achieved interesting results in LiDAR applications was tested for photogrammetric point clouds. The test was carried out by comparing the accuracy achieved by the new approach, which is based on the point density features of the analysed dataset, with those related to the more common local maxima and textural methods. The results indicated the potentiality of the density-based method, which achieved accuracy values (0.76 F-score) consistent with the traditional methods (0.49–0.80 F-score range) but was less affected by under- and over-fitting. Secondly, the potential improvement of working on intra-annual multi-temporal datasets was assessed by applying the density-based approach to seven different scenarios, three of which were constituted by single-epoch datasets and the remaining given by the joining of the others. The F-score increased from 0.67 to 0.76 when passing from single- to multi-epoch datasets, aligning with the accuracy achieved by the new method when applied to LiDAR data. The results demonstrate the potential of multi-temporal acquisitions when performing individual crown detection from photogrammetric data
Species‐By‐Species Pattern Analysis of Coastal Dune Vegetation
Full text linkVegetation is crucial for stabilizing and developing coastal dunes. Different plant species exhibit different spatial distributions which reflect their environmental role and adaptation strategy. This study aims to provide a fine-scale species-by-species analysis of vegetation spatial patterns on coastal dunes within the San Rossore–Migliarino–Massacciuccoli Regional Park (Tuscany, Italy). A comprehensive vegetation data set generated by an Object-Based Image Analysis (OBIA) algorithm applied to high-resolution ortho-images has been utilized. A Digital Terrain Model (DTM) of the study area was created to assess the impact of dune morphology on plant distribution. Moreover, a wave runup analysis was also conducted to understand the interaction between vegetation and hydrodynamic forces. The research highlights how the vegetation threshold distance from the coastline, Lveg, is superimposed by the reaching distance of wave runup during extreme events. Terrain morphology significantly affects the vegetation zonation: on taller and undisturbed dunefields, species zonation is clearer and more defined, whereas, on flatter and disturbed ones, spatial distribution is significantly fuzzier. A positive correlation emerges between the abundance of a species and its degree of spatial clustering, indicating how less abundant species form more tightly clustered spatial patterns. Modified Ripley's L-function analysis revealed a multi-scale clustered pattern for most species under examination. The present results may provide a solid benchmark in coastal ecology research for supporting natural-based conservation plans and eco-morphodynamic modeling
Raspberry pi 3 multispectral low-cost sensor for uav based remote sensing. case study in south-west Niger
Full text linkINTEGRATION OF UAV-LIDAR AND UAV-PHOTOGRAMMETRY FOR INFRASTRUCTURE MONITORING AND BRIDGE ASSESSMENT
Full text linkThe health assessment of strategic infrastructures and bridges represents a critical variable for planning appropriate maintenance operations. The high costs and complexity of traditional periodical monitoring with elevating platforms have driven the search for more efficient and flexible methods. Indeed, recent years have seen the growing diffusion and adoption of non-invasive approaches consisting in the use of Unmanned Aerial Vehicles (UAVs) for applications that range from visual inspection with optical sensors to LiDAR technologies for rapid mapping of the territory. This study defines two different methodologies for bridge inspection. A first approach involving the integration of traditional topographic and GNSS techniques with TLS and photogrammetry with cameras mounted on UAV was compared with a UAV-LiDAR method based on the use of a DJI Matrice 300 equipped with a LiDAR DJI Zenmuse L1 sensor for a manual flight and an automatic one. While the first workflow resulted in a centimetric accurate but time-consuming model, the UAV-LiDAR resulting point cloud’s georeferencing accuracy resulted to be less accurate in the case of the manual flight under the bridge for GNSS signal obstruction. However, a photogrammetric model reconstruction phase made with Ground Control Points and photos taken by the L1-embedded camera improved the overall accuracy of the workflow, that could be employed for flexible low-cost mapping of bridges when medium level accuracy (5–10 cm) is accepted. In conclusion, a solution for integrating interactively final 3D products in a Bridge Management System environment is presented
Analyzing Multitemporal Datasets to Monitor Topographic Changes in Rio Cucco Italy
Full text linkRio Cucco is an Italian catchment located in Malborghetto of Friuli Venezia Giulia. It is considered an area of interest regarding its hydrological and morphological properties. The area has historically been affected by natural hazards such as rockfall and landslides, mainly related to extreme rainfall events like the 2003 storm that affected the Fella river or the Vaia storm of October 2018. These events highlight the importance of understanding the morphological and topographic modification of the area also in relation to the realization of protection and hydraulic works. The changes in Rio Cucco were documented by comparing open-source historical data with ad-hoc UAV surveys focusing the analysis on 3D products like point clouds and the digital terrain models. The source of the recent data was an Aerial LiDAR- based survey conducted by our team in June 2024 while the historical data was taken from the FVG region’s geoportal and referred to 2017. After comparing the different datasets with traditional techniques like nearest neighbour Euclidean distance or DEM of Difference, changes were evident pointing to potential rockfalls between the year 2024 and 2017. A deep learning model was explored and in development for the semantic segmentation of the area
Detection of Wet Riparian Areas using Very High Resolution Multispectral UAS Imagery Based on a Feature-based Machine Learning Algorithm
Full text linkUnmanned Aerial System (UAS) imagery has
enabled very high-resolution multispectral image
acquisition. Detection of wet areas and classification of
land cover based on these images using the Machine
Learning (ML) algorithm named Random Forest (RF) is
our main purpose in this paper. Very high-resolution UAS
images have been used as inputs for a machine learner to
access the capability of different spectral bands and
spectral vegetation indices, elevation, and texture features
in the classification of land cover and detection of the wet
riparian area in the case study in two different epochs.
There are many existing methods for the classification of
land cover based on UAS images, but very high-resolution
centimeter-level data are of main importance in this
analysis. Outstanding results have been produced in both
epochs considering three extremely accurate performance
analysers. Additionally, in this research, the most decisive
and effective features have been discovered to
compromise accuracy and the number of effectual
features
Enhancing precision in coastal dunes vegetation mapping: ultra-high resolution hierarchical classification at the individual plant level
Full text linkThe classification of ultra-high-resolution (UHR) imagery, characterized by spatial resolutions exceeding 10 cm, presents opportunities and challenges distinct from lower-resolution counterparts. Particularly, challenges are pronounced in some scenarios, such as mapping plant species in coastal environments, where similar vegetation responses and small plant sizes pose additional difficulties. The present work addressed such issues by developing a UHR vegetation cover classification model at the single plant level using data from uncrewed aerial systems (UASs) equipped with a multispectral optical sensor. The model was tested across the San Rossore Regional Park (Italy), where three pilot areas were defined as training-test-validation sites. The proposed solution consists of a hierarchical two-level-of-detail machine learning model based on object-based image analysis (OBIA) and random forest. This model considers spectral features and indices, elevation, and texture and can classify twelve plant species and two service classes (debris and sand) within the study areas. Train and test were carried out utilizing UAS flight data collected during two specific phenological periods and precise field data derived from in-situ vegetation surveys, which provided 937 herbaceous and shrub samples. The model performance was evaluated based on the error matrix and 50-fold stratified cross-validation method, obtaining an overall accuracy (OA) of 0.76 and a standard deviation of 0.08. Such assessment underscored the crucial role of texture information, in addition to radiometric and elevation. Finally, the model was tested against an unseen dataset, proving its transferability (OA equal to 0.62). Although the discussion highlights some aspects to be further improved and claims for future research, the first version of this hierarchical classification model demonstrated its potential for mapping and monitoring coastal sand dune ecosystems, providing data for understanding and, eventually, modeling ecological and biogeomorphological dynamics
Biochar as biofertilizer
No full textBiochar application as biofertilizer in agriculture provides multiple advantages, such as enhancing soil quality, boosting crop productivity, and mitigating climate change. Biochar is rich in stable carbon and essential nutrients, and improves soil features as water retention, aeration, and nutrients’ availability. This reduces the need for chemical fertilizers and helps sequester carbon in the soil. When made from agricultural waste, biochar reduces waste and supports the circular economy by transforming waste materials into valuable resources, promoting a more sustainable agriculture.
In this study, the effect of biochar on the growth and development of strawberry plants was evaluated. Strawberry plants sprouts were rooted in commercial garden soil supplemented with biochar produced via pyrolysis of soft wood at 550°C. Biochar was dosed according to literature (2-12 tons/ha) involving 12 pots supplemented with biochar and 3 control (i.e. no biochar) pots placed in a lab-scale greenhouse. Biochar was applied unaltered and after physical activation with CO2 at 900°C. The growth and productivity of the plants was monitored for 3 months, recording plant height, number of flowers, and number of ripe fruits twice per week, and through continuous remote sensing. Specifically, a low-cost automated proximal sensor system was installed in the greenhouse to monitor the micro-climate and plant development. The system includes a MAPIR Survey 3W multispectral camera, a DHT22 temperature and humidity sensor, and five capacitive soil moisture sensors. The sensors were integrated using a Raspberry Pi 4 for data collection and storage. The 12 MP camera captured three spectral bands (550nm, 660nm, 850nm) with an 87° field of view and was positioned to capture all plants in one nadir image. Images were taken hourly, recording red, green, and near-infrared (RGN) spectral data, which allows for the calculation of vegetation indices (VIs) like the Normalized Difference Vegetation Index (NDVI) to estimate plant health. The correlation between NDVI and the biochar dose was investigated.
The average height of the plants supplemented with biochar was 16.35 ± 2.05 cm, with activated biochar was 16.3 ± 1.75 cm, and for the control group was 11.1 ± 1.30 cm. During the first month +17% net plant height was observed in the pots supplemented with biochar, but no significant difference was noticed between activated biochar and unaltered biochar (Figure 1). In terms of number of flowers and ripe fruits, the plants treated with biochar were 15 days beforehand when compared to control plants. Again, no evident difference was visible between activated and unaltered biochar.
This study was carried out within the Agritech National Research Center and received funding from the European Union Next-GenerationEU (PIANO NAZIONALE DI RIPRESA E RESILIENZA (PNRR) – MISSIONE 4 COMPONENTE 2, INVESTIMENTO 1.4 – D.D. 1032 17/06/2022, CN00000022)
- …
