Manual Digitization Research Articles

Monthly mapping of Indonesia’s burned areas: implementation, history, techniques, and future directions

ABSTRACT Forest and land fires cause substantial economic, social, and environmental devastation. Interagency forest and land fire management has succeeded in decreasing the impact of these fires, particularly in Indonesia. Having comprehensive information on fire locations and frequencies will benefit national forest and land fire management programmes. This study describes nearly a decade of satellite-based burned area (BA) monitoring conducted by the Indonesian government. We discuss (1) the history of BA mapping in Indonesia, (2) the most recent techniques for producing monthly BA maps, (3) an evaluation of product accuracy, (4) advantages and disadvantages, and (5) recommendations for future research. The most recent approach combines manual and digital classification, primarily using Landsat images, but has been supplemented with Sentinel data since 2020. The digital analysis, named the normalized burn ratio difference index threshold, was used to distinguish between burned and unburned pixels, guiding the interpreter’s manual digitization. BA confidence levels were determined using active fire products and ground truth data. We engaged provincial and local agency stakeholders to verify the products and provide quality assurance. We also assessed product performance by examining high-resolution images captured at three different locations to ascertain the relative advantages and disadvantages, which varied depending on each region’s fire regime. Small fires and cloud cover reduced the accuracy of the national monthly BA product. However, the omission error decreased by 65% when all fires throughout the entire year were considered. The inclusion of all available Sentinel-2 (A and B) images yielded higher accuracy than using only Landsat 8 data. We conclude that Indonesia’s cloud coverage constraint requires additional observational data to obtain clear-sky imagery when using optical sensors, in addition to the adjusted technique. We urge the introduction of reliable digital classifications for all Indonesian fire regimes to simplify resource deployment and reduce manual labour operations.

Rapid Appraisal of Wildlife Corridor Viability with Geospatial Modelling and Field Data: Lessons from Makuyuni, Tanzania

Connectivity between protected areas is necessary to prevent habitat fragmentation. Biodiverse countries like Tanzania craft legislation to promote habitat connectivity via the creation of ecological corridors, but their viability for wildlife often remains unknown. We therefore develop a scalable and replicable approach to assess and monitor multispecies corridor viability using geospatial modeling and field data. We apply and test the approach in the Makuyuni study area: an unprotected ecological corridor connecting Tarangire National Park to Essmingor mountain, Makuyuni Wildlife Park and Mto Wa Mbu Game Controlled Area. We analyzed the viability of Makuyuni as an ecological corridor by creating and validating a geospatial least-cost corridor model with field observations of wildlife and livestock. We created the model from publicly available spatial datasets augmented with manual digitization of pastoral homesteads (bomas). The least-cost corridor model identified two likely pathways for wildlife, confirmed and validated with field observations. Locations with low least-cost values were significantly correlated with more wildlife observations (Spearman’s rho = −0.448, p = 0.002). Our findings suggest that Makuyuni is a viable ecological corridor threatened by development and land use change. Our methodology presents a replicable approach for both monitoring Makuyuni and assessing corridor viability more generally. The incorporation of manually digitized homesteads (bomas) and field-based livestock observations makes corridor assessment more robust by taking into account pastoral land uses that are often missing in land cover maps. Integration of geospatial analysis and field observations is key for the robust identification of corridors for habitat connectivity.

Cobots at the Museum: The Role of Robotics in Digitisation

In the last decade, the Natural History Museum, UK (NHM), has been at the forefront of the digitisation of natural history collections, with almost six million of its 80 million specimens digitised. This momentous undertaking has led to numerous innovations on how to optimise digitisation workflows. One avenue that is currently being explored is the use of collaborative robots—cobots. Since acquiring a Techman TM5 900 robotic arm in 2023 (Scott et al. 2023), we have been experimenting with its capabilities. Experiments began with simple pick-and-place tasks, using artificial specimens. Next, we focused on two use-cases, based on the digitisation of shark teeth and pinned-insects. Both shark teeth and pinned insects are in abundance at the NHM, making their manual digitisation a tedious task. Currently, we have trained the cobot to pick up a specimen, move it elsewhere to photograph and scan the specimen, then move it back to its original position or to a new place. Thus far, this has all been coordinate-based. Focusing on pinned insect specimens, we have now begun training deep learning models to perform segmentation, classification, and tracking tasks on images and manually taken videos. Segmentation and classification tasks range from distinguishing specimens from one another within drawers, to classifying different pins, labels, and insects. Meanwhile, object tracking methods are utilised to track labels from videos taken around the specimen. By tracking different labels simultaneously from multiple frames, we can combine the views of the labels in order to obtain a full picture for each label (for example, using tools described in Salili-James et al. 2022). Thus far, our machine learning pipelines have proved successful, for example, with F1 scores of 96–98% to classify and segment insects and to locate pin heads from dorsal views. Soon, we will be establishing workflows that integrate computer vision (CV) and machine learning (ML) techniques directly with the robotic arm, with pipelines that could be applied to different datasets, and that can significantly enhance efficiency. Broadly, these pipelines can be split into four sections: Specimen Identification: CV/ML to locate individual specimens or certain parts of specimens e.g., pinheads within pinned insects. Handling: With custom grippers, the cobot can delicately pick up, move, and place specimens, to and from photography stations for high quality scanning. Imaging & Scanning: The cobot will scan and photograph specimens. As the camera moves around the specimen, ML is used to segment and track the specimen labels to image them from the optimal views. A built-in Optical Character Recognition process can also be integrated to perform automatic transcription from here. Identifiers: This step requires the cobot to attach identifier labels to specimens or drawers, after locating the optimal position to do this, using CV/ML. Specimen Identification: CV/ML to locate individual specimens or certain parts of specimens e.g., pinheads within pinned insects. Handling: With custom grippers, the cobot can delicately pick up, move, and place specimens, to and from photography stations for high quality scanning. Imaging & Scanning: The cobot will scan and photograph specimens. As the camera moves around the specimen, ML is used to segment and track the specimen labels to image them from the optimal views. A built-in Optical Character Recognition process can also be integrated to perform automatic transcription from here. Identifiers: This step requires the cobot to attach identifier labels to specimens or drawers, after locating the optimal position to do this, using CV/ML. In this talk, we will discuss the progress of the NHM’s cobot research and explore the future of robotics for the digitisation of natural history collections.

Mapping refugee populations at high resolution by unlocking humanitarian administrative data

BackgroundInforming local decision-making, improving service delivery and designing household surveys require having access to high-spatial resolution mapping of the targeted population. However, this detailed spatial information remains unavailable for specific population subgroups, such as refugees, a vulnerable group that would significantly benefit from focused interventions. Given the continuous increase in the number of refugees, reaching an all-time high of 35.3 million people in 2022, it is imperative to develop models that can accurately inform about their spatial locations, enabling better and more tailored assistance.MethodsWe leverage routinely collected registration data on refugees and combine it with high-resolution population maps, satellite imagery derived settlement maps and other spatial covariates to disaggregate observed refugee totals into 100-m grid cells. We suggest a deterministic grid cell allocation inside monitored refugee sites based on building count and a random-forest-derived grid cell allocation outside refugee sites based on geolocating the textual geographic information in the refugee register and on high-resolution population mapping. We test the method in Cameroon using the registration database monitored by the United Nations High Commissioner for Refugees.ResultsUsing OpenStreetMap, 83% of the manually inputted information in the registration database could be geolocated. The building footprint layer derived from satellite imagery by Ecopia AI offers extensive coverage within monitored refugee sites, although manual digitization was still required in rapidly evolving settings. The high-resolution mapping of refugees on a 100-m grid basis provides an unparalleled level of spatial detail, enabling valuable geospatial insights for informed local decision-making.ConclusionsGathering information on forcibly displaced persons in sparse data-setting environment can quickly become very costly. Therefore, it is critical to gain the most knowledge from operational data that is frequently collected, such as registration databases. Integrating it with ancillary information derived from satellite imagery paves the way for obtaining more timely and spatially precise information to better deliver services and enhance sampling frame for target data collection exercises that further improves the quality of information on people in need.

Satellite-based Spectral Indices for Extracting Village Water Bodies in Ludhiana District of Punjab, India

Ensuring water security is the foremost priority of every nation, and water bodies are the most precious life-sustaining resources on the earth. Availability of reliable and updated information of water bodies including knowledge about their locations is necessary for the sustainable planning and management of water resources at a regional scale. Remote sensing technique has revolutionized extraction of village water bodies as it provides fine spatial resolution, gives rapid and precise results and covers large areas, and hence, it has been widely used in the recent studies. In this study, three remote sensing-based spectral indices, i.e., normalized difference water index (NDWI), modified normalized difference water index (MNDWI), and normalized difference pond index (NDPI) were employed to demarcate the area of ponds in each village of Ludhiana district in Punjab. Accuracy of the spectral indices was evaluated by comparing the area of the ponds delineated by the indices with that of digitized manually. The results indicated that NDWI, MNDWI and NDPI could identify 370, 1263 and 1410 number of village ponds, respectively. On the other hand, a total of 1513 village ponds could be demarcated through manual digitization. Thus, the efficiency of NDWI in identification of correct number of village ponds was 24.5%, while the efficiency of MNDWI and NDPI was 83.5% and 93.2%, respectively. Furthermore, NDPI demonstrated an efficiency of 60-65% in demarcating the area of village ponds.

Influence of muscle packing on the three-dimensional architecture of rabbit M. plantaris

In their physiological condition, muscles are surrounded by connective tissue, other muscles and bone. These tissues exert transverse forces that change the three-dimensional shape of the muscle compared to its isolated condition, in which all surrounding tissues are removed. A change in shape affects the architecture of a muscle and therefore its mechanical properties. The rabbit M. plantaris is a multi-pennate calf muscle consisting of two compartments. A smaller, bi-pennate inner muscle compartment is embedded in a larger, uni-pennate outer compartment (Böl et al., 2015). As part of the calf, the plantaris is tightly packed between other muscles. It is unclear how packing affects the shape and architecture of the plantaris. Therefore, we examined the isolated and packed plantaris of the contralateral legs of three rabbits to determine the influence of the surrounding muscles on its shape and architectural properties using photogrammetric reconstruction and manual digitization, respectively. In the packed condition, the plantaris showed a 27% increase in fascicle pennation and a 54% increase in fascicle curvature compared to the isolated condition. Fascicle length was not affected by muscle packing. The change in muscle architecture occurred mainly in the outer compartment of the plantaris. Furthermore, the isolated plantaris showed a more circular shape and a reduced width of its muscle belly. It can be concluded that the packed plantaris is flattened by the forces exerted by the surrounding muscles, causing a complex architectural change. The data provided improve our understanding of muscle packages in general and can be used to develop and validate realistic three-dimensional muscle models.

Semantic Segmentation and Classification of Active and Abandoned Agricultural Fields through Deep Learning in the Southern Peruvian Andes

The monumental scale agricultural infrastructure systems built by Andean peoples during pre-Hispanic times have enabled intensive agriculture in the high-relief, arid/semi-arid landscape of the Southern Peruvian Andes. Large tracts of these labor-intensive systems have been abandoned, however, owing in large measure to a range of demographic, economic, and political crises precipitated by the Spanish invasion of the 16th century CE. This research seeks to better understand the dynamics of agricultural intensification and deintensification in the Andes by inventorying through the semantic segmentation of active and abandoned agricultural fields in satellite imagery across approximately 77,000 km2 of the Southern Peruvian Highlands. While manual digitization of agricultural fields in satellite imagery is time-consuming and labor-intensive, deep learning-based semantic segmentation makes it possible to map and classify en masse Andean agricultural infrastructure. Using high resolution satellite imagery, training and validation data were manually produced in distributed sample areas and were used to transfer-train a convolutional neural network for semantic segmentation. The resulting dataset was compared to manual surveys of the region and results suggest that deep learning can generate larger and more accurate datasets than those generated by hand.

Deep learning-based detection of qanat underground water distribution systems using HEXAGON spy satellite imagery

Qanats are a remarkable type of ancient hydraulic structure for sustainable water distribution in arid environments that use subterranean channels to transport water from highland or mountainous areas. The presence of the qanat system is marked by a line of regularly spaced shafts visible from the surface, which can be used to detect qanats using satellite imagery. Typically, qanats have been documented by field mapping or manual digitisation within a Geographic Information System (GIS) environment. This process is time-consuming due to the numerous shafts within each qanat line. However, several automated methods for detecting qanat structures have been explored, using techniques such as morphological filters, custom convolutional neural networks (CNN) and, more recently, YOLOv5 and Mask R-CNN. These approaches used high-resolution RGB images and CORONA images. However, the use of black and white CORONA in CNNs has been limited in its applicability due to a high rate of false positives.This paper explores the potential of YOLOv9 in processing the black and white HEXAGON (KH-9) high-resolution spy satellite system launched in 1971. Two areas in Afghanistan (Maiwand) and Iran (Gorgan Plain) were selected to train the system images extracted from HEXAGON imagery and artificial synthetic data. The training dataset was augmented using the Albumentation library, which increased the number of tiles used. The model was tested using two types of HEXAGON imagery for selected areas in Afghanistan (Maiwand), Iran (Gorgan Plain) and Morocco (Rissani), and CORONA imagery in Iran (Gorgan Plain).Our study provided a model capable of predicting the location of qanat shafts with a precision of over 0.881 and a recall of 0.627 for most of the case studies tested. This is the first case study aimed at detecting qanats in different landscapes using different types of satellite imagery. Using real, augmented, and artificial data allowed us to generalise the representation of qanats into lineal groups of circular features. Thanks to applying labelling for individual qanats and their pairs as separate classes, our approach eliminated most of the isolated and clustered false positives.

Best practices towards the digitization of 3D traces from virtual outcrop models

With the expanding application of virtual outcrop models (VOMs) within the geosciences, there is a growing need to establish standards for the digital measurement of geological discontinuities exposed therein. Such standards should be tailored towards the complexities of natural outcrops, where geological discontinuities often intersect the outcrop topography and are expressed as 3D traces. Digitizing geological discontinuities expressed as trace data is typically conducted manually via polyline interpolation along the exposed trace, with discontinuity orientation estimated through planar model fitting through the polyline's component nodes. Presently, establishing quality control for such measurements lacks standardization due to the absence of robust benchmarks, with the validity of the resultant orientation data heavily reliant on the experience of the interpreter.With the aim of bridging this gap, we present the results of the manual digitization and orientation estimation of bedding planes expressed as traces across seven natural outcrops. We use two digitization strategies: one employing a previewed best-fit plane during digitization and another without. The first digitization method is carried out by an expert user who visually filters data according to visual alignment with the intended bedding prior to best fit plane estimation. In contrast, the non-visually aided method mimics acquisition by a novice user, with no a priori data filtering based upon trace geometry with respect to the outcrop. Comparison of the results obtained by these ‘expert’ and ‘novice’ acquisition modes is aimed at building benchmarks and best practices. Specifically, we analyze parameters derived from the digitized traces and their corresponding best-fit planes. We compare these parameters with the deviation of the best-fit plane from the mean orientation of the bedding surface as measured using visually-aided acquisition. Comparing these datasets reveals that visually-aided digitization yields more precise and accurate bedding measurements, characterized by traces with lower vertex collinearity. Notably, comparable results can be achieved in the non-visually assisted dataset by excluding traces with high node collinearity. Consequently, we provide robust benchmarks for trace collinearity and its relationship to best fit plane quality to aid the practical implementation of the results of this study. Furthermore, we supplement quantitative comparative analysis with recommended best practices for 3D trace digitization, such as ensuring high values of coplanarity, maintaining a quasi-constant node-to-node distance relative to the model's resolution, and ensuring a minimum number of nodes to guarantee the robustness of the fitted planar model. Critically, our study highlights the critical role tacit geological knowledge plays in the robustness of 3D trace digitization from virtual outcrop models.

SurvdigitizeR: an algorithm for automated survival curve digitization

BackgroundDecision analytic models and meta-analyses often rely on survival probabilities that are digitized from published Kaplan–Meier (KM) curves. However, manually extracting these probabilities from KM curves is time-consuming, expensive, and error-prone. We developed an efficient and accurate algorithm that automates extraction of survival probabilities from KM curves.MethodsThe automated digitization algorithm processes images from a JPG or PNG format, converts them in their hue, saturation, and lightness scale and uses optical character recognition to detect axis location and labels. It also uses a k-medoids clustering algorithm to separate multiple overlapping curves on the same figure. To validate performance, we generated survival plots form random time-to-event data from a sample size of 25, 50, 150, and 250, 1000 individuals split into 1,2, or 3 treatment arms. We assumed an exponential distribution and applied random censoring. We compared automated digitization and manual digitization performed by well-trained researchers. We calculated the root mean squared error (RMSE) at 100-time points for both methods. The algorithm’s performance was also evaluated by Bland–Altman analysis for the agreement between automated and manual digitization on a real-world set of published KM curves.ResultsThe automated digitizer accurately identified survival probabilities over time in the simulated KM curves. The average RMSE for automated digitization was 0.012, while manual digitization had an average RMSE of 0.014. Its performance was negatively correlated with the number of curves in a figure and the presence of censoring markers. In real-world scenarios, automated digitization and manual digitization showed very close agreement.ConclusionsThe algorithm streamlines the digitization process and requires minimal user input. It effectively digitized KM curves in simulated and real-world scenarios, demonstrating accuracy comparable to conventional manual digitization. The algorithm has been developed as an open-source R package and as a Shiny application and is available on GitHub: https://github.com/Pechli-Lab/SurvdigitizeR and https://pechlilab.shinyapps.io/SurvdigitizeR/.

Evaluating Shoreline Changes at Ayvacık Reservoir (Çanakkale, Türkiye) Through Remote Sensing and Geographic Information System Techniques: A Twelve-Year Assessment

This study aims to determine the spatial and temporal changes occurring along the shoreline of the Ayvacık Reservoir in Çanakkale, Türkiye. Landsat 8 OLI/TIRS and Landsat 7 ETM+ satellite images were analyzed using remote sensing and geographic information system techniques. The dataset used in the study covers the period between the completion of the dam construction in 2008 and 2019. Preprocessing of the remote sensing satellite images and digital image processing analyses were carried out using ENVI and ArcGIS software. The shoreline was determined through manual digitization. Consequently, it was found that the shoreline length was 14.994 km in 2008 and increased to 22.293 km in 2019. These values represent the observed minimum and maximum shoreline lengths, respectively. The study period revealed an increase in shoreline length. Given that this study is the first to elucidate shoreline changes occurring at the Ayvacık Reservoir, it is anticipated to provide essential insights for water resource managers by contributing significantly to the literature.

Variability in depth for national-level swimmers’ freestyle dive starts, push starts and tumble turns

The dive start and tumble turn are key skills in freestyle swimming and are the fastest part of a race (Higgs, Pease & Sanders, 2016, J Sports Sci, 35, 995-1003). Consistency in performing them, to a high-level, is crucial when races can be won by <0.1s. Many studies have investigated dives, tumble turns and underwater undulatory swimming performance, however, very few have examined the effect of depth (West et al., 2022, Sports Med Open, 8). Swimming depth will affect wave drag, total distance travelled underwater and, possibly, kick amplitude. Collectively, these will impact dive and tumble turn performance. The current project aims to quantify the variability of a swimmer’s freely chosen depth when performing a freestyle dive start, push start and turn. Ethics approval for this study was provided by the School of Medicine’s Research ethics board. We aim to recruit 14 participants (7=male, 7=female), over the age of 16 and currently competing at a national level in freestyle events. After a 10-min self-determined warm-up, participants are asked to perform three freestyle dives, push starts, and tumble turns in a randomised order. There are three minutes rest between each task and five minutes between three tasks. Each of the nine tasks will be recorded using a custom-built CONTEMPLAS camera system, using 12 cameras filming at 100Hz. Participants are provided with 5-min to complete a self-determined cool-down. Video recordings will be analysed using SIMI Motion capture to perform manual digitisation. A coefficient of variance analysis and a repeated measures Anova and intraclass correlation to quantify the variability in depth within the dives, push starts and the turns at both an individual and group level. As part of this study, we are also assessing the reliability and validity of an automated digitising software package. The validity and reliability of the automatic digitisation method versus the manual digitisation method was analysed via a Bland Altman analysis to obtain the limits of agreement between the two methodologies. The results are pending, although they will be used to assign individual swimmers with target depth ranges for subsequent experiments that aim to identify the optimum depth for these skills.

Pemanfaatan Citra Satelit Untuk Mengidentifikasi Perubahan Bentang Lahan

This study explores the use of satellite imagery in identifying and monitoring landscape change in the context of sustainable development and natural resource management. The research method used is literature study, by collecting, reviewing and analyzing various sources of information relevant to the research topic. The results of the analysis show that satellite imagery, especially from the Landsat satellite, plays an important role in mapping land use changes over a long period of time, which is useful for monitoring and analyzing land change. Various techniques and methods, such as manual digitization, use of GIS, and guided classification methods, are used to identify landscape changes. Factors such as sensor technology, image processing, ground truth data, and the complexity of the study environment influence the precision and accuracy of analysis results. The conclusion of this study is that the use of satellite imagery in managing and monitoring landscape change provides significant benefits in the context of sustainable development, but also requires a long-term and inclusive approach to ensure the use of this technology can take place effectively and sustainably.

Using image segmentation models to analyse high-resolution earth observation data: new tools to monitor disease risks in changing environments.

In the near future, the incidence of mosquito-borne diseases may expand to new sites due to changes in temperature and rainfall patterns caused by climate change. Therefore, there is a need to use recent technological advances to improve vector surveillance methodologies. Unoccupied Aerial Vehicles (UAVs), often called drones, have been used to collect high-resolution imagery to map detailed information on mosquito habitats and direct control measures to specific areas. Supervised classification approaches have been largely used to automatically detect vector habitats. However, manual data labelling for model training limits their use for rapid responses. Open-source foundation models such as the Meta AI Segment Anything Model (SAM) can facilitate the manual digitalization of high-resolution images. This pre-trained model can assist in extracting features of interest in a diverse range of images. Here, we evaluated the performance of SAM through the Samgeo package, a Python-based wrapper for geospatial data, as it has not been applied to analyse remote sensing images for epidemiological studies. We tested the identification of two land cover classes of interest: water bodies and human settlements, using different UAV acquired imagery across five malaria-endemic areas in Africa, South America, and Southeast Asia. We employed manually placed point prompts and text prompts associated with specific classes of interest to guide the image segmentation and assessed the performance in the different geographic contexts. An average Dice coefficient value of 0.67 was obtained for buildings segmentation and 0.73 for water bodies using point prompts. Regarding the use of text prompts, the highest Dice coefficient value reached 0.72 for buildings and 0.70 for water bodies. Nevertheless, the performance was closely dependent on each object, landscape characteristics and selected words, resulting in varying performance. Recent models such as SAM can potentially assist manual digitalization of imagery by vector control programs, quickly identifying key features when surveying an area of interest. However, accurate segmentation still requires user-provided manual prompts and corrections to obtain precise segmentation. Further evaluations are necessary, especially for applications in rural areas.

VedgeSat: An automated, open‐source toolkit for coastal change monitoring using satellite‐derived vegetation edges

AbstractPublic satellite platforms offer regular observations for global coastal monitoring and climate change risk management strategies. Unfortunately, shoreline positions derived from satellite imagery, representing changes in intertidal topography, are noisy and subject to tidal bias that requires correction. The seaward‐most vegetation boundary reflects a change indicator which shifts on event–decadal timescales, and informs coastal practitioners of storm damage, sediment availability and coastal landform health. We present and validate a new open‐source tool VedgeSat for identifying vegetation edges (VEs) from high (3 m) and moderate (10–30 m) resolution satellite imagery. The methodology is based on the CoastSat toolkit, with streamlined image processing using cloud‐based data management via Google Earth Engine. Images are classified using a newly trained vegetation‐specific neural network, and VEs are extracted at subpixel level using dynamic Weighted Peaks thresholding. We performed validation against ground surveys and manual digitisation of aerial imagery across eroding and accreting open coasts and estuarine environments at a site in Scotland. Smaller‐than‐pixel vegetation boundary detection was achieved across 83% of Sentinel‐2 imagery (Root Mean Square Error of 9.3 m). An overall RMSE of 19.0 m was achieved across Landsat 5 & 8, Sentinel‐2 and PlanetScope images. Performance varied by coastal geomorphology, with highest accuracies across sandy open coasts owing to high spectral contrast and less false positives from intertidal vegetation. The VedgeSat tool can be readily applied in tandem with waterlines near‐globally, to support adaptation decisions with historic coastal trends across the whole shoreface, even in normally data‐scarce areas.

Fractional cover mapping of wildland-urban interface fuels using Landsat, Sentinel 1 and PALSAR imagery

Fuels within the immediate vicinity of a house (e.g., within 30–60 m), referred to as the ‘home-ignition zone’, are important determinants of structure damage during wildfires. Methods for mapping home-ignition zone fuels using earth observing satellites are lacking, limiting the capacity to quantify the spatial and temporal dynamics of urban fuel hazard and wildfire risk. Here, we (i) develop a methodology to map the fractional cover of five common fuel types (i.e., bare, buildings, herbaceous, woody and water cover) at the scale of the home-ignition zone (45 m radius area) using Landsat, Sentinel 1, and PALSAR imagery, and (ii) demonstrate that these maps improve prediction of house loss in wildfires in western Canada. A fractional cover database was created across thirteen cities via manual digitisation of aerial photos and used to train and validate random forest models consisting of combinations of Landsat, Sentinel 1 and PALSAR indices. The best models for the fractional cover of each fuel type explained most of the variation in the data (R2 = 0.66–0.96) and had high accuracy (Mean absolute error = 0.02–0.11) with low bias (Mean error = −0.005–0.008). The combination of optical (Landsat) and synthetic aperture radar (Sentinel 1 and/or PALSAR) improved model accuracy relative to models containing only multi-spectral indices. A house loss database was then derived for five major fires in western Canada and used to examine the effect of mapped fractional cover on house loss rates for 227 neighbourhood blocks. House loss rates were greater in blocks with a low amount of defensible space (i.e., areas of low fuel hazard; bare, herbaceous, or water cover) surrounding houses compared to those with extensive defensible space. This finding is consistent with house loss research globally and exposure assessment guidelines for communities in North America. Our fuel cover mapping methodology will facilitate improvements to models of house loss through the inclusion of important home-ignition zone fuel properties, allowing for spatially and temporally dynamic (i.e., annual) estimates of house loss likelihood and wildfire risk to communities.

Enhancing surface drainage mapping in eastern Canada with deep learning applied to LiDAR-derived elevation data.

Agricultural dykelands in Nova Scotia rely heavily on a surface drainage technique called land forming, which is used to alter the topography of fields to improve drainage. The presence of land-formed fields provides useful information to better understand land utilization on these lands vulnerable to rising sea levels. Current field boundaries delineation and classification methods, such as manual digitalization and traditional segmentation techniques, are labour-intensive and often require manual and time-consuming parameter selection. In recent years, deep learning (DL) techniques, including convolutional neural networks and Mask R-CNN, have shown promising results in object recognition, image classification, and segmentation tasks. However, there is a gap in applying these techniques to detecting surface drainage patterns on agricultural fields. This paper develops and tests a Mask R-CNN model for detecting land-formed fields on agricultural dykelands using LiDAR-derived elevation data. Specifically, our approach focuses on identifying groups of pixels as cohesive objects within the imagery, a method that represents a significant advancement over pixel-by-pixel classification techniques. The DL model developed in this study demonstrated a strong overall performance, with a mean Average Precision (mAP) of 0.89 across Intersection over Union (IoU) thresholds from 0.5 to 0.95, indicating its effectiveness in detecting land-formed fields. Results also revealed that 53% of Nova Scotia's dykelands are being used for agricultural purposes and approximately 75% (6924 hectares) of these fields were land-formed. By applying deep learning techniques to LiDAR-derived elevation data, this study offers novel insights into surface drainage mapping, enhancing the capability for precise and efficient agricultural land management in regions vulnerable to environmental changes.

Comparison of failure modes and effects analyses and time for brachytherapy ring and tandem applicator digitization between manual and solid applicator source placement methods.

Ring and tandem (R&T) applicator digitization is currently performed at our institution by manually defining the extent of the applicators. Digitization can also be achieved using solid applicators: predefined, 3D models with geometric constraints. This study compares R&T digitization using manual and solid applicator methods through Failure Modes and Effects Analyses (FMEAs) and comparative time studies. We aim to assess the suitability of solid applicator method implementation for R&T cases METHODS: Six qualified medical physicists (QMPs) and two medical physics residents scored potential modes of failure of manual digitization in an FMEA as recommended by TG-100. Occurrence, severity, and detectability (OSD) values were averaged across respondents and then multiplied to form combined Risk Priority Numbers (RPNs) for analysis. Participants were trained to perform treatment planning using a developed solid applicator protocol and asked to score a second FMEA on the distinct process steps from the manual method. For both methods, participant digitization was timed. FMEA and time data were analyzed across methods and participant samples RESULTS: QMPs rated the RPNs of the current, manual method of digitization statistically lower than residents did. When comparing the unique FMEA steps between the two digitization methods, QMP respondents found no significant difference in RPN means. Residents, however, rated the solid applicator method as higher risk. Further, after the solid applicator method was performed twice by participants, the time to digitize plans was not significantly different from manual digitization CONCLUSIONS: This study indicates the non-inferiority of the solid applicator method to manual digitization in terms of risk, according to QMPs, and time, across all participants. Differences were found in FMEA evaluation and solid applicator technique adoption based on years of brachytherapy experience. Further practice with the solid applicator protocol is recommended because familiarity is expected to lower FMEA occurrence ratings and further reduce digitization times.

Application of a novel deep learning-based 3D videography workflow to bat flight.

Studying the detailed biomechanics of flying animals requires accurate three-dimensional coordinates for key anatomical landmarks. Traditionally, this relies on manually digitizing animal videos, a labor-intensive task that scales poorly with increasing framerates and numbers of cameras. Here, we present a workflow that combines deep learning-powered automatic digitization with filtering and correction of mislabeled points using quality metrics from deep learning and 3D reconstruction. We tested our workflow using a particularly challenging scenario: bat flight. First, we documented four bats flying steadily in a 2 m3 wind tunnel test section. Wing kinematic parameters resulting from manually digitizing bats with markers applied to anatomical landmarks were not significantly different from those resulting from applying our workflow to the same bats without markers for five out of six parameters. Second, we compared coordinates from manual digitization against those yielded via our workflow for bats flying freely in a 344 m3 enclosure. Average distance between coordinates from our workflow and those from manual digitization was less than a millimeter larger than the average human-to-human coordinate distance. The improved efficiency of our workflow has the potential to increase the scalability of studies on animal flight biomechanics.

Nation-scale multidecadal shoreline extraction and coastal spatio-temporal change monitoring using cross-mission remote sensing data

Mapping shorelines is critical for coastal management and conservation, as shorelines are essential indicators for understanding coastal geomorphology and dynamics. Nonetheless, as shorelines are often lengthy and rugged, in-situ surveys are labor-intensive and costly. Oppositely, spaceborne remote sensing data provide cost-efficient alternatives, yet, most earlier studies rely on manual digitization or thresholding band ratio-based water indices to delineate instantaneous shorelines, which locations are affected by varying water color and tides. Consequently, cross-temporal assessments of environmental and anthropogenic impacts on coastal stability remain challenging. The present study develops an edge detection-based, dual-temporal, nationwide, tide-coordinated, and sediment cell-based shoreline dataset in Japan, i.e., the TSSD-JP. Both 1980s and 2020s shorelines along the Japanese coasts are extracted using cross-mission multispectral data and an automated shoreline extraction method. The results are validated with national coast surveys and global shoreline databases, confirming a positional accuracy better than 80% at 50 m. Moreover, founded on the extracted dual-temporal shorelines, 30+ year coastal changes are measured. An increased land area of 293.21 km2 at a rate of 8.50 km2/yr is estimated. Evident accretions in bay regions of southern Honshu due to extensive land reclamation and engineering constructions are observed. Since the analysis is conducted on natural management units with a physical basis, potential biases caused by jurisdictional boundaries are overcome. Practically, because TSSD-JP is derived from freely accessible data and tools, its universal applicability is guaranteed. Thence, the proposed approach can be applied to different nations' intertidal zones to assess the coastal vulnerability and resilience as well as support local governments’ shoreline management plans (SMPs).