Milto Miltiadou

Monitoring forest health has become essential due to increasing pressures caused by climate change and dust events, particularly in semi-arid regions. This study investigates the impact of dust events on forest vegetation in Paphos forest in Cyprus, which is a semi-arid area prone to frequent dust storms. Using multispectral and radar satellite data from Sentinel-1 and Landsat series, vegetation responses to eight documented dust events between 2015 and 2019 were analysed, employing BFAST (Breaks For Additive Season and Trend) algorithms to detect abrupt changes in vegetation indices and radar backscatter. The outcomes showed that radar data were particularly effective in identifying only the most significant dust events (PM10 > 100 μg/m³, PM2.5 > 30 μg/m³), indicating that SAR (Synthetic Aperture Radar) is more responsive to pronounced dust deposition, where backscatter changes reflect more substantial vegetation stress. Conversely, optical data were sensitive to a wider range of events, capturing responses even at lower dust concentrations (PM10 > 50 μg/m³, PM2.5 > 20 μg/m³) and detecting minor vegetation stress through indices like SAVI, EVI, and AVI. The analysis highlighted that successful detection relies on multiple factors beyond sensor type, such as rainfall timing and imagery availability close to the dust events. This study highlights the importance of an integrated remote sensing approach for effective forest health monitoring in regions prone to dust events.

Large scale forest inventory plot data are key to monitor forest ecosystems, but while they provide very detailed information at tree level they are limited in resolution in both space and through time. Earth Observation (EO) data offer the opportunity for scaling up plot data and improving the temporal resolution of monitoring. However, there are significant challenges to this, including small field plot sizes, pre-processing and potential GPS errors in aligning the data, whilst the huge amount and variety of EO data introduce substantial challenges of high dimensionality, in addition to the noise of training and testing data, within any AI system. In this work, we fuse plot and Earth Observation data, demonstrating the value of embedding existing and newly EO derived metrics, and selecting the most important features to improve monitoring of forest properties at large scales. In this work we work with Sentinel-1 (SAR) and Sentinel-2 (optical) and inventory data from close to 10,000 plots in Spain, measured from onwards. SAR data require substantial pre-processing due to noise and acquisition, topographic and moisture effects. We used pre-processed SAR data, and filtered for non-shaded slopes, removed plots close to surface water and data collected on days with high precipitation. We masked out clouds from our optical data. After fusing the EO data, we removed disturbed areas using the Global Forest Change Collection and plots with high variability of pixels around them to reduce uncertainty due to the small sizes of the plots. As well as using standard indices (e.g., NDVI, RVI), we derive new metrics of the phenological cycle of the forest from monthly averages of indices and bands by selecting features from peaks and troughs. We reduce dimensionality using principal component analysis and random forest to select the most important features. Chosen features are used for training and evaluating a customized AI system to estimate forest variables such as total basal area, stem density, mean diameter at breast height and forest type. The code implemented in Google Earth Engine JavaScript and Python will be released as open source.

This study experiments with different combinations of UAV hyperspectral data and LiDAR metrics for classifying eight tree species found in a Brazilian Atlantic Forest remnant, the most degraded Brazilian biome with high fragmentation but with huge structural complexity. The selection of the species was done based on the number of tree samples, which exist in the plot data and in the fact the UAV imagery does not acquire information below the forest canopy. Due to the complexity of the forest, only species that exist in the upper canopy of the remnant were included in the classification. A combination of hyperspectral UAV images and LiDAR point clouds were in the experiment. The hyperspectral images were photogrammetric and radiometric processed to obtain orthomosaics with reflectance factor values. Raw spectra were extracted from the trees, and vegetation indices (VIs) were calculated. Regarding the LiDAR data, both the point cloud—referred to as Peak Returns (PR)—and the full-waveform (FWF) LiDAR were included in this study. The point clouds were processed to normalize the intensities and heights, and different metrics for each data type (PR and FWF) were extracted. Segmentation was preformed semi-automatically using the superpixel algorithm, followed with manual correction to ensure precise tree crown delineation before tree species classification. Thirteen different classification scenarios were tested. The scenarios included spectral features and LiDAR metrics either combined or not. The best result was obtained with all features transformed with principal component analysis with an accuracy of 76%, which did not differ significantly from the scenarios using the raw spectra or VIs with PR or FWF LiDAR metrics. The combination of spectral data with geometric information from LiDAR improved the classification of tree species in a complex tropical forest, and these results can serve to inform management and conservation practices of these forest remnants.

With the rise in high resolution remote sensing technologies there has been an explosion in the amount of data available for forest monitoring, and an accompanying growth in artificial intelligence applications to automatically derive forest properties of interest from these datasets. Many studies use their own data at small spatio-temporal scales, and demonstrate an application of an existing or adapted data science method for a particular task. This approach often involves intensive and time-consuming data collection and processing, but generates results restricted to specific ecosystems and sensor types. There is a lack of widespread acknowledgement of how the types and structures of data used affects performance and accuracy of analysis algorithms. To accelerate progress in the field more efficiently, benchmarking datasets upon which methods can be tested and compared are sorely needed. Here, we discuss how lack of standardisation impacts confidence in estimation of key forest properties, and how considerations of data collection need to be accounted for in assessing method performance. We present pragmatic requirements and considerations for the creation of rigorous, useful benchmarking datasets for forest monitoring applications, and discuss how tools from modern data science can improve use of existing data. We list a set of example large-scale datasets that could contribute to benchmarking, and present a vision for how community-driven, representative benchmarking initiatives could benefit the field.

This study aims to investigate how alternations of the land surface temperature (LST) affects the normalized difference vegetation index (NDVI) in Paphos forest, Cyprus, using Landsat-5 and Landsat-8 imagery for the time periods 1993–2000 and 2013–2018, respectively. A total of 262 Landsat images were processed to compute the mean monthly NDVI and LST values and create a time series. Using the Cook’s distance, the effect of missing values in the analysis of the time series were examined. Results from the cross-correlation and cross-variograms, decomposition model, and the BFAST algorithm were compared to produce reliable conclusions on forest changes and satellite, meteorological, and environmental data were combined to interpret the changes that occurred inside the forest. The decomposition analysis showed a decrease of 2.7% in the LST for the period 1993–2000 and an increase of 4.6% in the LST during the period 2013–2018. The NDVI trend is negatively correlated to the LST trend for both time periods. An increase in the LST trend was identified in November 1998 as well as in the NDVI trend in October 1994 and May 2014 that was caused by favorable climatic conditions. An increase in the NDVI trend from May 2014 to December 2015 may be related to reduced pityocampa attacks. An abrupt decrease was detected in December 2015 that was probably caused by the locust invasion that occurred in the island earlier that year. A positive correlation appears for LST and NDVI variables for time lags 4, 5, 6, 7, and 8 months. Overall, it was shown that LST and NDVI analysis is very promising for identifying potential forest decline.

Recent reports stress the vulnerability of forest ecosystems in the European Union (EU), especially in the south. Cyprus is an island in the south of EU and the eastern of the Mediterranean Sea. While Cyprus’ vulnerability is stressed, Cyprus was included in the worst-performing countries regarding EU carbon emission’s targets of 2020. For mitigating climate change, Cyprus could benefit for tailored education and improved policy making. This study analyses the perceptions of the Cypriot residents about climate change and forest degradation aiming (1) to gain a better understanding of whether Cypriot residents understand its importance, (2) to understand if the general public is able to observe the changes noted in the literature, (3) to understand how perceptions are differentiated across different demographic categories, and (4) to derive correlations between demographic data and perceptions. This is a quantitative study; a questionnaire was used as a tool and the responses received were 416. It was highlighted that 65.62% of the participants stated that they noticed moderate to very much degradation of Cypriot coniferous forests. A potential degradation reason was written down by 150 people, of whom 31.33% referred to tree die-back, while many stated decreased soil moisture and difficulty in regeneration. All these reasons of degradation were either stated or suspected in the literature. Additionally, the demographic analysis showed that there may be an association between employability and beliefs/observations about climate change. The results of the research could be used for tailored education, further research, and promoting environmentally friendly policies. This will support Cyprus and other countries in reaching their Green Deal targets and, consequently, mitigate the severe effects of climate change.

Data collection and estimation of variables that describe the structure of tropical forests, diversity, and richness of tree species are challenging tasks. Light detection and ranging (LiDAR) is a powerful technique due to its ability to penetrate small openings and cracks in the forest canopy, enabling the collection of structural information in complex forests. Our objective was to identify the most significant LiDAR metrics and machine learning techniques to estimate the stand and diversity variables in a disturbed heterogeneous tropical forest. Data were collected in a remnant of the Brazilian Atlantic Forest with different successional stages. LiDAR metrics were used in three types of transformation: (i) raw data (untransformed), (ii) correlation analysis, and (iii) principal component analysis (PCA). These transformations were tested with four machine learning techniques: (i) artificial neural network (ANN), ordinary least squares (OLS), random forests (RF), and support vector machine (SVM) with different configurations resulting in 27 combinations. The best technique was determined based on the lowest RMSE (%) and corrected Akaike information criterion (AICc), and bias (%) values close to zero. The output forest variables were mean diameter at breast height (MDBH), quadratic mean diameter (QMD), basal area (BA), density (DEN), number of tree species (NTS), as well as Shannon–Waver (H’) and Simpson’s diversity indices (D). The best input data were the new variables obtained from the PCA, and the best modeling method was ANN with two hidden layers for the variables MDBH, QMD, BA, and DEN while for NTS, H’and D, the ANN with three hidden layers were the best methods. For MDBH, QMD, H’and D, the RMSE was 5.2–10% with a bias between −1.7% and 3.6%. The BA, DEN, and NTS were the most difficult variables to estimate, due to their complexity in tropical forests; the RMSE was 16.2–27.6% and the bias between −12.4% and −0.24%. The results showed that it is possible to estimate the stand and diversity variables in heterogeneous forests with LiDAR data.

In this paper, we investigate the performance of six data structures for managing voxelised full-waveform airborne LiDAR data during 3D polygonal model creation. While full-waveform LiDAR data has been available for over a decade, extraction of peak points is the most widely used approach of interpreting them. The increased information stored within the waveform data makes interpretation and handling difficult. It is, therefore, important to research which data structures are more appropriate for storing and interpreting the data. In this paper, we investigate the performance of six data structures while voxelising and interpreting full-waveform LiDAR data for 3D polygonal model creation. The data structures are tested in terms of time efficiency and memory consumption during run-time and are the following: (1) 1D-Array that guarantees coherent memory allocation, (2) Voxel Hashing, which uses a hash table for storing the intensity values (3) Octree (4) Integral Volumes that allows finding the sum of any cuboid area in constant time, (5) Octree Max/Min, which is an upgraded octree and (6) Integral Octree, which is proposed here and it is an attempt to combine the benefits of octrees and Integral Volumes. In this paper, it is shown that Integral Volumes is the more time efficient data structure but it requires the most memory allocation. Furthermore, 1D-Array and Integral Volumes require the allocation of coherent space in memory including the empty voxels, while Voxel Hashing and the octree related data structures do not require to allocate memory for empty voxels. These data structures, therefore, and as shown in the test conducted, allocate less memory. To sum up, there is a need to investigate how the LiDAR data are stored in memory. Each tested data structure has different benefits and downsides; therefore, each application should be examined individually.