Object-based Image Analysis Research Articles

Flooded area detection and mapping from Sentinel-1 imagery. Complementary approaches and comparative performance evaluation

ABSTRACT The current study assesses the performance of several machine learning (ML) and deep learning (DL) models for detecting and mapping floods using Sentinel-1 SAR imagery. Three distinct approaches were used: pixel classification, object-based image analysis and object instance segmentation. The ML models are Random Forest, and Support Vector Machine and the DL models are U-NET, DeepLabV3 and Mask RCNN. Five different case studies were selected to test the models’ scalability. These areas are in Romania (Prut River, at the border between Romania, the Republic of Moldova and Ukraine, Timiș River, and Râul Negru River), the United States of America (Missouri River) and Australia (Broughton Creek). For each flood, five Sentinel-1 images were used, four collected before the flood and one collected after the flood. The intensity images were stacked and scaled in the range of the intensity thresholds associated with water and non-water so that all the case studies have the same margins for intensity. Samples of water, vegetation, agricultural fields, and bare soil were collected only from the Prut River case study and used in the training process. Out of all models, the U-Net model returned the highest accuracy with a value for Intersect over Union of 0.763 for a tile size of 128x128 pixels.

Mangroves Invaded by Spartina alterniflora Loisel: A Remote Sensing-Based Comparison for Two Protected Areas in China

Mangroves are one of the world’s most productive and ecologically important ecosystems, and they are threatened by the widespread invasion of Spartina alterniflora Loisel in China. As few studies have examined the spatial pattern differences of S. alterniflora invasion and the nearby mangroves in different latitudes, we chose the Zhangjiang Estuary and the Dandou Sea, two representative mangrove–salt marsh ecotones in the north and south of the Tropic of Cancer, as the study areas for comparison. The object-based image analysis and visual interpretation methods were combined to construct fine-scale mangrove and S. alterniflora maps using high-resolution satellite imagery from 2005 to 2019. We applied spatial analysis, centroid migration, and landscape indexes to analyze the spatio–temporal distribution changes of mangroves and S. alterniflora in these two ecotones over time. We used the landscape expansion index to investigate the S. alterniflora invasion process and expansion patterns. The annual change rates of mangrove and S. alterniflora areas in the Zhangjiang Estuary showed a continuous growth trend. However, the mangrove areas in the Dandou Sea showed a fluctuating trend of increasing, decreasing, and then increasing again, while S. alterniflora areas kept rising from 2005 to 2019. Spartina alterniflora showed larger annual change rates compared with mangroves, indicating rapid S. alterniflora invasion in the intertidal zones. The opposite centroid migration directions of mangroves and S. alterniflora and the decreasing distances between the mangrove and S. alterniflora centroids indirectly revealed the fierce competition between mangroves and S. alterniflora for habitat resources. Both regions saw a decrease in mangrove patch integrality and connectivity. The integrality of mangrove patches in the Zhangjiang Estuary was always higher than those in the Dandou Sea. We observed the growth stage (2011–2014) and outbreak stage (2014–2019) of S. alterniflora expansion in the Zhangjiang Estuary and the outbreak stage (2005–2009) and plateau stage (2009–2019) of S. alterniflora expansion in the Dandou Sea. The expansion pattern of S. alterniflora varies in time and place. Since the expansion of S. alterniflora in the outbreak stage is rapid, with a large annual change rate, early warning of S. alterniflora invasion is quite important for the efficient and economical removal of the invasive plant. Continuous and accurate monitoring of S. alterniflora is highly necessary and beneficial for the scientific management and sustainable development of coastal wetlands.

Occupancy dynamics of the mottled owl Strix virgata using object-based image analysis along an urbanized Neotropical gradient

Urbanization has profound effects on wildlife. Although some species benefit or even thrive in urban environments, most species respond differently to the varying degrees of disturbance that can be found across an urbanized landscape. Quantifying the effects of urbanization in wildlife distributions, however, is complicated: species vary in their patterns of presence/absence, abundance, and detectability across spatial and temporal scales, e.g., daily, seasonal, or throughout the annual cycle. Here, we use occupancy models to offer a realistic approach to the study of populations of urban owls. Most studies on owl population dynamics have not considered temporal variation in occupancy between seasons or assess the uneven effects of urbanization along a habitat gradient. We investigated the seasonal habitat associations of mottled owls along an urban gradient in the Neotropical city of Xalapa, Veracruz, Mexico. Using high-resolution satellite images and object-based image classification techniques, were analyzed the relationship between different vegetation and environmental characteristics with the occupancy of mottled owls. We employed different sampling techniques, including playback surveys and silent listening periods, to detect the presence or absence of owls along a gradient from highest to lowest urbanization. Environmental data and different vegetation types were used to analyze the habitat associations of mottled owls during January (late non-breeding season) and May (late breeding season) of 2023. In total, we detected 68 mottled owls during the non-breeding season and 102 during the breeding season, with higher detection rates in areas with >28 % forest surface. Our results revealed that the best occupancy model included forest and forest division (occupancy), ambient noise and moonlight (detection) for the non-breeding season, as well as urban, forest, grass, and forest division (occupancy), and noise (detection) for the breeding season. The percentage of forested and grass areas positively influenced mottled owl occupancy while the percentage of urbanization and forest division influenced it negatively. Moonlight was positively related to mottled owl detection, while ambient noise had a negative effect on detection probabilities of mottled owls during both seasons. Forested areas emerged as pivotal for owl occupancy, indicating their sensitivity to forest changes along the urban gradient. With urban areas increasing, the interplay between forest division, ambient noise, and moonlight unveils critical insights into mottled owl behavior and habitat dynamics, underscoring the necessity for informed conservation strategies amidst urban expansion. Future research should survey different years to provide a more robust assessment of the dynamic occupancy of mottled owls in Neotropical urban gradients.

Integrating UAV imagery and machine learning via Geographic Object Based Image Analysis (GEOBIA) for enhanced monitoring of Yucca gloriosa in Mediterranean coastal dunes

Effective monitoring and early detection of invasive alien plant species (IAPs) are crucial for mitigating their spread and safeguarding native habitats. Unmanned Aerial Vehicles (UAVs) offer a cost-efficient solution, providing high resolution images. In this study, we aimed to develop a semi-automated methodology using a machine learning algorithm, spatial metrics, and clustering techniques on UAV images to monitor, map, and suggest management measures to counteract Yucca gloriosa, an invasive plant colonizing coastal fixed dunes in central Italy.UAV flights were conducted using two drones: one for the visible spectrum and the other for multispectral bands (Blue, Green, Red, Red Edge, and Near Infrared) along with a Digital Surface Model (DSM). Derived vegetation indices were also utilized. For mapping Y. gloriosa distribution, a Geographic Object Based Image Analysis (GEOBIA) approach was applied to the orthophoto segmentation, followed by a Random Forest algorithm in a training phase, considering three variable combinations (DSM + vegetation indices, DSM + spectral bands, DSM + mixed variables). The most accurate Y. gloriosa map was used to suggest management measures combining the spatial pattern of invaded patches (size, height, isolation level, and aggregation degree) and a mixed clustering approach (hierarchical and partitioning).The results highlighted that the most accurate prediction map was based on the DSM + mixed variables dataset, showing the important role of using a combination of spectral bands and vegetation indices. In all three cases, the DSM emerged as the pivotal variable for discriminating Y. gloriosa from the surrounding environment. Additionally, our results demonstrate the advantages of incorporating vegetation indices in discerning the target invasive alien plant (IAP) from the broader environment, particularly considering its distinctive photosynthesis process and biomass production. From a managerial standpoint, our pilot study indicates that the UAV-based mapping methodology represents an optimal balance between field efforts and costs. This approach allows for the precise identification of containment and removal areas of Y. gloriosa, without compromising the accuracy of the method. The generated prediction maps also hold potential significance for the conservation of coastal dune ecosystems, providing a promising tool for the effective management of invasive species and biodiversity conservation by suggesting management measures for Y. gloriosa.

Crop Growth Analysis Using Automatic Annotations and Transfer Learning in Multi-Date Aerial Images and Ortho-Mosaics

Growth monitoring of crops is a crucial aspect of precision agriculture, essential for optimal yield prediction and resource allocation. Traditional crop growth monitoring methods are labor-intensive and prone to errors. This study introduces an automated segmentation pipeline utilizing multi-date aerial images and ortho-mosaics to monitor the growth of cauliflower crops (Brassica Oleracea var. Botrytis) using an object-based image analysis approach. The methodology employs YOLOv8, a Grounding Detection Transformer with Improved Denoising Anchor Boxes (DINO), and the Segment Anything Model (SAM) for automatic annotation and segmentation. The YOLOv8 model was trained using aerial image datasets, which then facilitated the training of the Grounded Segment Anything Model framework. This approach generated automatic annotations and segmentation masks, classifying crop rows for temporal monitoring and growth estimation. The study’s findings utilized a multi-modal monitoring approach to highlight the efficiency of this automated system in providing accurate crop growth analysis, promoting informed decision-making in crop management and sustainable agricultural practices. The results indicate consistent and comparable growth patterns between aerial images and ortho-mosaics, with significant periods of rapid expansion and minor fluctuations over time. The results also indicated a correlation between the time and method of observation which paves a future possibility of integration of such techniques aimed at increasing the accuracy in crop growth monitoring based on automatically derived temporal crop row segmentation masks.

A novel hybrid methodology integrating pixel- and object-based techniques for mapping land use and land cover from high-resolution satellite data

ABSTRACT The classification of very high-resolution satellite imagery remains a focal point in remote sensing, attracting increased attention across diverse scientific disciplines. Various classification methods, including pixel- and object-based techniques, have been proposed, and their performances and limitations have been discussed in the literature. This paper presents a hybrid method that combines the strengths of pixel- and object-based methods in image classification to minimize errors associated with the segmentation process, particularly under-segmentation errors in object-based image analysis. The core concept behind the method lies in categorizing segmented image objects as either homogeneous or heterogeneous based on their class probability. In this process, the estimated possibilities from the object-based classification model are considered, and segments are designated as homogeneous or heterogeneous using a user-defined threshold. The object-based classification model determines the class labels for homogeneous image objects, while the heterogeneous ones, containing pixels representing different land cover classes, are classified using the pixel-based model. The performance of hybrid classification models, created by varying thresholds, is analysed using high-resolution WorldView-3 and WorldView-2 imagery and compared with pixel- and object-based classification results. For the implementation of image classification methods, Canonical Correlation Forest (CCF), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost) were employed. The findings indicated that employing the suggested hybrid strategy with a threshold value selected within a specific range (e.g. between 60% and 80%) and employing a robust classification algorithm that provides class probabilities (e.g. CCF) results in a statistically significant improvement in overall accuracy compared to pixel and object-based methods, with gains of 5% and 4%, respectively. Visual analysis of the produced thematic maps revealed that the proposed method minimizes the salt-and-pepper effect associated with pixel-based classification while mitigating segmentation problems arising from object-based classification.

Synergistic approach for land use and land cover dynamics prediction in Uttarakhand using cellular automata and Artificial neural network

Alterations in Land use and Land cover (LULC) stand out as a key catalyst for shifts in global climate patterns, environmental conditions, and ecological dynamics. In order to further enhance our comprehension of the effects of variability and climate shifts on the environment, Remote sensing and GIS analytical approaches have been thoroughly explored and are reflected in an imperative vision. Thus, the objective of this study is to model Uttarakhand’s LULC pattern for 2032 and analyse changes in Uttarakhand's LULC trend between 1992 and 2022. LULC change mapping was conducted utilizing a semi-automated hybrid classification approach for high level of accuracy which integrates both Maximum likelihood and Object based image analysis classification techniques on Landsat datasets. The machine learning techniques of Cellular automata and Artificial neural networks (CA-ANN) within MOLUSCE plugin of QGIS have been applied to model future LULC patterns. The accuracy assessment results showed that the overall accuracy of LULC for the years 1992, 2002, 2012, and 2022 was 96.94 %, 97.77 %, 98.61 % and 98.87 % respectively, and the overall kappa statistics coefficient was 0.92, 0.95, 0.94 and 0.95 respectively. The simulated and projected LULC map for 2022 implies a substantially high level of accuracy, with an overall Kappa coefficient value of 0.77 % and 85.39 % of overall correctness. Then, LULC changes for the year 2032 are predicted using CA-ANN. The observed alterations between 1992 and 2032 are significant, characterized by an augmentation in built-up areas, open land, and water bodies, alongside a decline in snow-covered regions, vegetation cover. Whereas, a slight increase is seen in Forested areas. Planners and policy makers aiming to accomplish a more sustainable future and efficient management of the environment will find the changes in LULC over a prolonged period of time to be a useful asset for optimal land use planning.

Correction to “Object‐Based Image Analysis (OBIA)‐based gully erosion dynamics, sediment loading rate and sediment yield study in Lake Hawassa Subbasin, Ethiopia”

Correction to “Object‐Based Image Analysis (OBIA)‐based gully erosion dynamics, sediment loading rate and sediment yield study in Lake Hawassa Subbasin, Ethiopia”

Ensemble Machine Learning on the Fusion of Sentinel Time Series Imagery with High-Resolution Orthoimagery for Improved Land Use/Land Cover Mapping

In the United States, several land use and land cover (LULC) data sets are available based on satellite data, but these data sets often fail to accurately represent features on the ground. Alternatively, detailed mapping of heterogeneous landscapes for informed decision-making is possible using high spatial resolution orthoimagery from the National Agricultural Imagery Program (NAIP). However, large-area mapping at this resolution remains challenging due to radiometric differences among scenes, landscape heterogeneity, and computational limitations. Various machine learning (ML) techniques have shown promise in improving LULC maps. The primary purposes of this study were to evaluate bagging (Random Forest, RF), boosting (Gradient Boosting Machines [GBM] and extreme gradient boosting [XGB]), and stacking ensemble ML models. We used these techniques on a time series of Sentinel 2A data and NAIP orthoimagery to create a LULC map of a portion of Irion and Tom Green counties in Texas (USA). We created several spectral indices, structural variables, and geometry-based variables, reducing the dimensionality of features generated on Sentinel and NAIP data. We then compared accuracy based on random cross-validation without accounting for spatial autocorrelation and target-oriented cross-validation accounting for spatial structures of the training data set. Comparison of random and target-oriented cross-validation results showed that autocorrelation in the training data offered overestimation ranging from 2% to 3.5%. The XGB-boosted stacking ensemble on-base learners (RF, XGB, and GBM) improved model performance over individual base learners. We show that meta-learners are just as sensitive to overfitting as base models, as these algorithms are not designed to account for spatial information. Finally, we show that the fusion of Sentinel 2A data with NAIP data improves land use/land cover classification using geographic object-based image analysis.

Mapping tree species of wetlands using multispectral images of UAVs and machine learning: A case study of the Dong Rui Commune

Wetlands provide resources, regulate the environment, and stabilize shorelines; however, they are among the most vulnerable ecosystems in the world. The classification of mangrove species allows the determination of the habitat of each species, thereby serving as a basis for determining protection solutions and planning plans for mangrove conservation and restoration according to each environmental condition. We used Phantom 4 multispectral unmanned aerial vehicles (UAVs) to collect data from wetland areas in the Dong Rui Commune, which is one of the most diverse and valuable wetland ecosystems in northern Vietnam. A tree-species classification map was constructed through a combination of the object-based image analysis method and spectral reflectance values of each plant species, and the characteristic distributions of mangrove plants, including Bruguiera gymnorrhiza, Rhizophora stylosa, and Kandelia obovata, were determined with an overall accuracy of 91.11 % and a kappa coefficient (K) of 0.87. The overall accuracy for Rhizophora stylosa was the highest (94.23 %), followed by Kandelia obovata (93.61 %) and Bruguiera gymnorrhiza (85.50 %). An experiment was conducted to map plant taxonomy in the same area based only on a graph of spectral reflectance values at five single-spectral bands, and normalized difference vegetation index values were constructed, resulting in an overall accuracy of 78.22 % and a K of 0.67. The constructed map is useful for classifying, monitoring, and evaluating the structure of each group of mangroves, thereby serving as a basis for determining the distribution of each mangrove species according to natural conditions and contributing to the formulation of policies for afforestation and mangrove conservation in Dong Rui commune.

Object-based image analysis for extracting regional slope units and its application

Object-based image analysis for extracting regional slope units and its application

Agroforestry area mapping using medium resolution satellite data and object-based image analysis

Agroforestry is gaining increased attention within global policy processes and has been promoted as a strategy for working towards better food security, climate change adaptation and mitigation and livelihood resilience. With this gaining importance of agroforestry, site-specific studies are required to delineate different agroforestry systems and estimate the exact area under agroforestry. In this study remote sensing and GIS techniques were used for the estimation of area under agroforestry using medium-resolution satellite (sentinel 2A and 2B) data. Agroforestry area classification and estimation were done in e-Cognition developer software (10.0 version) through multiresolution segmentation and object-based image analysis (OBIA). The agroforestry area estimated in the erstwhile Warangal district was 3753 ha with an overall accuracy of 86% and a kappa coefficient of 0.84. The major agroforestry systems observed in the erstwhile Warangal district were eucalyptus, subabul, malabar neem, teak, sandalwood and red sanders.

Enhancing precision in coastal dunes vegetation mapping: ultra-high resolution hierarchical classification at the individual plant level

ABSTRACT The 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.

Exploring agricultural landscape change from the second half of the twentieth century onwards: combining aerial imagery with farmer perspectives

ContextAnthropogenic landscape change is an important driver shaping our environment. Historical landscape analysis contributes to the monitoring and understanding of these change processes. Such analyses are often focused on specific spatial scales and single research methods, thus covering only limited aspects of landscape change.ObjectivesHere, we aim to assess the potential of combining the analysis of historical aerial imagery and local stakeholder interviews for landscape change studies using a standardized mapping and interviewing approach.MethodsWe compared six agricultural landscapes across Europe and mapped land-cover using historical aerial imagery (starting between 1930 and 1980, depending on data availability, until recent years) with an object-based image analysis and random forest classification. For local perspectives of landscape change, we conducted oral history interviews (OHIs) with (almost) retired farmers. Comparing recorded landscape changes from both approaches provided insight into advantages of combining these two methods.ResultsObject-based analysis enabled the identification of high-resolution land-cover dynamics, with scale enlargement and cropland/grassland expansion being the most commonly recurring trends across European landscapes. Perceived landscape changes identified in the OHIs included changes in farm management, landscape structure, and infrastructure. Farmers also reported drivers and personal values associated with landscape change. Combining the two historical landscape analysis tools resulted in a qualitative and quantitative understanding of changes in land-cover, land use, and land management.ConclusionsComparing physical land-cover change with local farmer perspectives is key to a comprehensive understanding of landscape change. There are different ways the two methods can be combined, leading to different venues for science and policy making.

Quantification of species composition in grass-clover swards using RGB and multispectral UAV imagery and machine learning.

Growing grass-legume mixtures for forage production improves both yield productivity and nutritional quality, while also benefiting the environment by promoting species biodiversity and enhancing soil fertility (through nitrogen fixation). Consequently, assessing legume proportions in grass-legume mixed swards is essential for breeding and cultivation. This study introduces an approach for automated classification and mapping of species in mixed grass-clover swards using object-based image analysis (OBIA). The OBIA procedure was established for both RGB and ten band multispectral (MS) images capturedby an unmanned aerial vehicle (UAV). The workflow integrated structural (canopy heights) and spectral variables (bands, vegetation indices) along with a machine learning algorithm (Random Forest) to perform image segmentation and classification. Spatial k-fold cross-validation was employed to assess accuracy. Results demonstrated good performance, achieving an overall accuracy of approximately 70%, for both RGB and MS-based imagery, with grass and clover classes yielding similar F1 scores, exceeding 0.7 values. The effectiveness of the OBIA procedure and classification was examined by analyzing correlations between predicted clover fractions and dry matter yield (DMY) proportions. This quantification revealed a positive and strong relationship, with R2 values exceeding 0.8 for RGB and MS-based classification outcomes. This indicates the potential of estimating (relative) clover coverage, which could assist breeders but also farmers in a precision agriculture context.

Assessing the contribution of RGB VIs in improving building extraction from RGB-UAV images

Buildings are a fundamental component of the built environment, and accurate information regarding their size, location, and distribution is vital for various purposes. The ever-increasing capabilities of unmanned aerial vehicles (UAVs) have sparked an interest in exploring various techniques to delineate buildings from the very high-resolution images obtained from UAV photogrammetry. However, the limited spectral information in UAV images, particularly the number of bands, can hinder the differentiation between various materials and objects. This setback can affect the ability to distinguish between different materials and objects. To address this limitation, vegetative ındices (VIs) have been employed to enhance the spectral strength of UAV orthophotos, thereby improving building classification. The objective of this study is to evaluate the contribution of four specific VIs: the green leaf index (GLI), red-green-blue vegetation index (RGBVI), visual atmospherically resistant index (VARI), and triangular greenness index (TGI). The significance of this contribution lies in assessing the potential of each VI to enhance building classification. The approach utilized the geographic object-based image analysis (GeoBIA) approach and a random forest classifier. To achieve this aim, five datasets were created, with each dataset comprising the RGB-UAV image and a corresponding RGB VI. The experimental results on the test dataset and a post-classification assessment indicated a general improvement in the classification when the VIs were added to the RGB orthophoto.

Target-based building extraction from high-resolution RGB imagery using GEOBIA framework and tabular deep learning model

Extracting building information from remotely sensed images is essential in various geographic and environmental applications. Specifically, there is a growing demand for distinguishing buildings based on roof colors from low-cost but high-resolution RGB images. However, this task presents significant challenges due to the variability in building color, size, and style, as well as their resemblance to nonbuilding objects. The existing GEographic Object-Based Image Analysis (GEOBIA) approaches often struggle with misclassification, mainly because they do not effectively leverage spatial information during the classification stage. Tabular Deep Learning (DL) models have emerged as promising alternatives to shallow classifiers, demonstrating improved performance in recent years. However, their effectiveness in extracting buildings based on roof color has not been thoroughly examined. To address these challenges and improve the accuracy of building extraction, this study proposed a target-based model that incorporates a sequential extraction process using tabular DL models such as Gated Additive Tree Ensemble (GATE), Neural Oblivious Decision Ensemble (NODE). The proposed method adopted a hybrid segmentation approach to effectively segment the image and extract each segment's spectral, textural, geometrical, and contextual features. Non-building objects were systematically eliminated based on their representation within the image. Subsequently, buildings with varying roof colors—brown, black, and white—were extracted. Spatial information was then meticulously integrated into the classification process. The proposed methodology was tested on a UAV image with a spatial resolution of 0.20 m and three visible bands—red, green, and blue—captured in Kingston, Ontario, Canada. This enhanced approach significantly improved precision and overall classification accuracy, demonstrating the effectiveness of incorporating spatial data into the extraction process. This research introduced a framework for incorporating spatial information into tabular models that would serve as a foundation for further improving building extraction accuracy in future studies.

Upscaling net ecosystem CO2 exchanges in croplands: The application of integrating object-based image analysis and machine learning approaches

Accurately estimating the net ecosystem exchange of CO2 (NEE) in cropland ecosystems is essential for understanding the impacts of agricultural practices and climate conditions. However, significant uncertainties persist in the estimation of regional cropland NEE due to landscape heterogeneity and variations in the efficacy of upscaling models. Here, we applied an integrated approach that combined object-based image analysis (OBIA) techniques with advanced machine learning (ML) approaches to upscale regional cropland NEE. We conducted a thorough evaluation of the upscaling approach across four distinct cropland areas characterized by diverse climate conditions. Our study confirmed that OBIA techniques can efficiently segment cropland objects, thereby enhancing the representation and accuracy of characteristics relevant to cropland features. The sequential least squares programming algorithm, among the three methods used for ML model integration, demonstrated exceptional performance in predicting NEE, with an R2 value exceeding 0.80 across all study areas and peaking at 0.90 in the most successful area. On average, there was an 18 % improvement compared to the poorest-performing ML model and a 6 % enhancement compared to the best-performing ML model. The upscaled regional products exhibited superior performance in characterizing cropland NEE patterns compared to pixel-based products. Additionally, we utilized the SHapley Additive exPlanations (SHAP) to assess driver importance, revealing that phenology and radiation had the greatest influence on prediction accuracy, followed by temperature and soil moisture. This study highlights the potential of integrating OBIA techniques with machine learning approaches for upscaling regional cropland NEE, while concurrently reducing estimation uncertainties.

Time-Efficient Low-Resolution RGB Aerial Imaging for Precision Mapping of Weed Types in Site-Specific Herbicide Application

An efficient method for weed detection and the precise generation of spraying maps is crucial to optimising weed management strategies and minimising the costs associated with herbicide use. This study presents a method that leverages low-resolution UAV images to accurately detect and map weeds in sugarcane fields. The proposed approach integrates RGB images, vegetation indices and the HSV colour space, enhancing segmentation through histogram equalization (HE) and object-based image analysis (OBIA). The models developed in this study demonstrate exceptional performance in weed detection, with the most suitable dataset, achieving a detection capability of 95.78% for Broad-leaved Weeds (BLW) and the highest accuracy of 94.45% for Narrow-leaved Weeds (NLW). When considering multiple targets such as BLW, NLW, soil and sugarcane, the models exhibit a detection accuracy of 89.69%. Furthermore, the precision spraying maps generated by the coverage model method (CM) demonstrate remarkable accuracy, reaching 97.50% for weed control using agricultural drones. This method offers an efficient, cost-effective, and timely solution for precise weed detection, leading to improved weed control outcomes by enabling the selection of appropriate chemical substances tailored to each weed species. It reduces repetitive spraying costs and minimises chemical usage through spot spraying.

Effects of the Architectural Layout of the Sanctuary of Pachacamac (2nd–16th Century CE, Peru) on the Exposure to Rain, Wind, and Solar Radiation from the Morphometric Analysis of Digital Surface Models

Natural events (floods, earthquakes, landslides, etc.) may significantly damage archaeological sites, and therefore reducing their exposure to such events represents a priority for protective and conservation activities. The archaeological Sanctuary of Pachacamac (SP; 2nd–16th century CE; Peru) covers an area of 465 hectares and includes roads, enclosures, huacas with ramps, temples, and palaces located along the central coast of Peru. This area is affected by heavy rain and winds related to the El Niño–Southern Oscillation and to intense solar radiation. We use a 30 cm resolution Digital Surface Model obtained from orthophotogrammetric data and perform a morphometric analysis using geomorphological, hydrological, and climatic quantitative parameters. Our aim is to identify the zones exposed to water flow or stagnation during rainfall, as well as the exposure to winds and solar radiation. The calculated parameters are subsequently processed with an object-based image analysis approach to identify areas with higher climate exposure. We show that the SP architectural layout controls the exposure to water stagnation or flow in the form of rainfall, whereas exposure to wind and solar radiation mainly depends on the topography of an area (e.g., the presence of hills and plains). The methodological approach proposed here may be applied and extended to other archaeological sites.