A temporal segmentation approach for dendrometers signal-to-noise discrimination

Francini, Saverio; Cocozza, Claudia; Hölttä, Teemu; Lintunen, Anna; Paljakka, Teemu; Chirici, Gherardo; Traversi, Maria Laura; Giovannelli, Alessio

doi:10.1016/j.compag.2023.107925

Cited by 4 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As it is considered suitable for continuous data populations and forestry studies [67], the nearest neighbour method was applied to complete the following tasks: (1) to resample our canopy height maps (10 m) to the resolution of ALS-based CHM map (1 m); and (2) to check errors in raster alignment and adjust alignment using ALS-based CHM map as snap raster. Subsequently, we applied Cook's distance method to remove influential values (outliers) from pixel values from the predicted and reference maps [68][69][70]. Then, the predicted and reference data were compared using the linear regression model.…”

Section: Comparison Of Predicted Canopy Height Maps With Reference Ai...mentioning

confidence: 99%

High-Resolution Canopy Height Mapping: Integrating NASA’s Global Ecosystem Dynamics Investigation (GEDI) with Multi-Source Remote Sensing Data

Alvites,

O’Sullivan,

Francini

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Accurate structural information about forests, including canopy heights and diameters, is crucial for quantifying tree volume, biomass, and carbon stocks, enabling effective forest ecosystem management, particularly in response to changing environmental conditions. Since late 2018, NASA’s Global Ecosystem Dynamics Investigation (GEDI) mission has monitored global canopy structure using a satellite Light Detection and Ranging (LiDAR) instrument. While GEDI has collected billions of LiDAR shots across a near-global range (between 51.6°N and >51.6°S), their spatial distribution remains dispersed, posing challenges for achieving complete forest coverage. This study proposes and evaluates an approach that generates high-resolution canopy height maps by integrating GEDI data with Sentinel-1, Sentinel-2, and topographical ancillary data through three machine learning (ML) algorithms: random forests (RF), gradient tree boost (GB), and classification and regression trees (CART). To achieve this, the secondary aims included the following: (1) to assess the performance of three ML algorithms, RF, GB, and CART, in predicting canopy heights, (2) to evaluate the performance of our canopy height maps using reference canopy height from canopy height models (CHMs), and (3) to compare our canopy height maps with other two existing canopy height maps. RF and GB were the top-performing algorithms, achieving the best 13.32% and 16% root mean squared error for broadleaf and coniferous forests, respectively. Validation of the proposed approach revealed that the 100th and 98th percentile, followed by the average of the 75th, 90th, 95th, and 100th percentiles (AVG), were the most accurate GEDI metrics for predicting real canopy heights. Comparisons between predicted and reference CHMs demonstrated accurate predictions for coniferous stands (R-squared = 0.45, RMSE = 29.16%).

show abstract

Section: Comparison Of Predicted Canopy Height Maps With Reference Ai...mentioning

confidence: 99%

High-Resolution Canopy Height Mapping: Integrating NASA’s Global Ecosystem Dynamics Investigation (GEDI) with Multi-Source Remote Sensing Data

Alvites,

O’Sullivan,

Francini

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The GEE platform is a cloud-based solution that combines a huge, multi-petabyte collection of satellite images and geospatial datasets with the capability of large-scale planetary analysis [ 24 ]. Its global applications span various sectors, including forestry and forest disturbance monitoring [ 7 , 12 , 30 ]. GEE boasts three key advantages over other cloud-computing platforms.…”

Section: The Datadriven Open Source Toolmentioning

confidence: 99%

“…dataDriven preprocesses Sentinel-2 data to construct cloud-free composites over different periods. The main steps involve (1) the filtering of Sentinel-2 imagery, (2) cloud masking, and (3) creating pixel-based composites [ 30 ]. dataDriven can filter Sentinel-2 imagery by specifying the period, the years of interest, and the maximum percentage of clouds.…”

Section: The Datadriven Open Source Toolmentioning

confidence: 99%

“…Other products concern the per-pixel accuracy of maps that, as usual in forest studies, are obtained using geostatistical or machine learning approaches. In the case of geostatistical mapping, accuracy estimation is performed from a series of more or less realistic model assumptions (e.g., [ 15 ], Equation (20.15), while in the case of machine learning procedures, accuracy estimation is usually performed from empirical cross-validation procedures [ 30 ] but lacks theoretical foundations. On the other hand, the procedure we adopted in this study stems from a theoretical study by [ 46 ] and provides per-pixel, statistically rigorous, design-based estimates of map accuracy.…”

Section: Future Perspectivesmentioning

confidence: 99%

“…The open accessibility of data and cloud computing platforms that enable the calculation of sophisticated information globally [ 24 , 25 , 26 ] characterize the current era of remote sensing. To improve the reliability of remote sensing products and exploit them in order to provide statistically rigorous estimates for large-scale or country reporting, huge efforts have been developed in recent years [ 27 , 28 , 29 , 30 ]. However, several limitations persist, leading many researchers and authorities to lean towards ground data acquisition.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Per-Pixel Forest Attribute Mapping and Error Estimation: The Google Earth Engine and R dataDriven Tool

Francini,

Marcelli,

Chirici

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

Remote sensing products are typically assessed using a single accuracy estimate for the entire map, despite significant variations in accuracy across different map areas or classes. Estimating per-pixel uncertainty is a major challenge for enhancing the usability and potential of remote sensing products. This paper introduces the dataDriven open access tool, a novel statistical design-based approach that specifically addresses this issue by estimating per-pixel uncertainty through a bootstrap resampling procedure. Leveraging Sentinel-2 remote sensing data as auxiliary information, the capabilities of the Google Earth Engine cloud computing platform, and the R programming language, dataDriven can be applied in any world region and variables of interest. In this study, the dataDriven tool was tested in the Rincine forest estate study area—eastern Tuscany, Italy—focusing on volume density as the variable of interest. The average volume density was 0.042, corresponding to 420 m3 per hectare. The estimated pixel errors ranged between 93 m3 and 979 m3 per hectare and were 285 m3 per hectare on average. The ability to produce error estimates for each pixel in the map is a novel aspect in the context of the current advances in remote sensing and forest monitoring and assessment. It constitutes a significant support in forest management applications and also a powerful communication tool since it informs users about areas where map estimates are unreliable, at the same time highlighting the areas where the information provided via the map is more trustworthy. In light of this, the dataDriven tool aims to support researchers and practitioners in the spatially exhaustive use of remote sensing-derived products and map validation.

show abstract

Field-independent carbon mapping and quantification in forest plantation through remote sensing

Francini,

Vangi,

D’Amico

et al. 2024

European Journal of Remote Sensing

View full text Add to dashboard Cite

A temporal segmentation approach for dendrometers signal-to-noise discrimination

Cited by 4 publications

References 53 publications

High-Resolution Canopy Height Mapping: Integrating NASA’s Global Ecosystem Dynamics Investigation (GEDI) with Multi-Source Remote Sensing Data

High-Resolution Canopy Height Mapping: Integrating NASA’s Global Ecosystem Dynamics Investigation (GEDI) with Multi-Source Remote Sensing Data

Per-Pixel Forest Attribute Mapping and Error Estimation: The Google Earth Engine and R dataDriven Tool

Field-independent carbon mapping and quantification in forest plantation through remote sensing

Contact Info

Product

Resources

About