1. |
- Abdi, A. M., et al.
(author)
-
First assessment of the plant phenology index (PPI) for estimating gross primary productivity in African semi-arid ecosystems
- 2019
-
In: International Journal of Applied Earth Observation and Geoinformation. - : Elsevier BV. - 1569-8432. ; 78, s. 249-260
-
Journal article (peer-reviewed)abstract
- The importance of semi-arid ecosystems in the global carbon cycle as sinks for CO 2 emissions has recently been highlighted. Africa is a carbon sink and nearly half its area comprises arid and semi-arid ecosystems. However, there are uncertainties regarding CO 2 fluxes for semi-arid ecosystems in Africa, particularly savannas and dry tropical woodlands. In order to improve on existing remote-sensing based methods for estimating carbon uptake across semi-arid Africa we applied and tested the recently developed plant phenology index (PPI). We developed a PPI-based model estimating gross primary productivity (GPP) that accounts for canopy water stress, and compared it against three other Earth observation-based GPP models: the temperature and greenness (T-G) model, the greenness and radiation (GöR) model and a light use efficiency model (MOD17). The models were evaluated against in situ data from four semi-arid sites in Africa with varying tree canopy cover (3–65%). Evaluation results from the four GPP models showed reasonable agreement with in situ GPP measured from eddy covariance flux towers (EC GPP) based on coefficient of variation (R 2 ), root-mean-square error (RMSE), and Bayesian information criterion (BIC). The GöR model produced R 2 = 0.73, RMSE = 1.45 g C m −2 d −1 , and BIC = 678; the T-G model produced R 2 = 0.68, RMSE = 1.57 g C m −2 d −1 , and BIC = 707; the MOD17 model produced R 2 = 0.49, RMSE = 1.98 g C m −2 d −1 , and BIC = 800. The PPI-based GPP model was able to capture the magnitude of EC GPP better than the other tested models (R 2 = 0.77, RMSE = 1.32 g C m −2 d −1 , and BIC = 631). These results show that a PPI-based GPP model is a promising tool for the estimation of GPP in the semi-arid ecosystems of Africa.
|
|
2. |
- Abid, Nosheen, 1993-, et al.
(author)
-
UCL: Unsupervised Curriculum Learning for Water Body Classification from Remote Sensing Imagery
- 2021
-
In: International Journal of Applied Earth Observation and Geoinformation. - : Elsevier. - 1569-8432 .- 1872-826X. ; 105
-
Journal article (peer-reviewed)abstract
- This paper presents a Convolutional Neural Networks (CNN) based Unsupervised Curriculum Learning approach for the recognition of water bodies to overcome the stated challenges for remote sensing based RGB imagery. The unsupervised nature of the presented algorithm eliminates the need for labelled training data. The problem is cast as a two class clustering problem (water and non-water), while clustering is done on deep features obtained by a pre-trained CNN. After initial clusters have been identified, representative samples from each cluster are chosen by the unsupervised curriculum learning algorithm for fine-tuning the feature extractor. The stated process is repeated iteratively until convergence. Three datasets have been used to evaluate the approach and show its effectiveness on varying scales: (i) SAT-6 dataset comprising high resolution aircraft images, (ii) Sentinel-2 of EuroSAT, comprising remote sensing images with low resolution, and (iii) PakSAT, a new dataset we created for this study. PakSAT is the first Pakistani Sentinel-2 dataset designed to classify water bodies of Pakistan. Extensive experiments on these datasets demonstrate the progressive learning behaviour of UCL and reported promising results of water classification on all three datasets. The obtained accuracies outperform the supervised methods in domain adaptation, demonstrating the effectiveness of the proposed algorithm.
|
|
3. |
- Araza, Arnan, et al.
(author)
-
Past decade above-ground biomass change comparisons from four multi-temporal global maps
- 2023
-
In: International Journal of Applied Earth Observation and Geoinformation. - 1569-8432. ; 118
-
Journal article (peer-reviewed)abstract
- Above-ground biomass (AGB) is considered an essential climate variable that underpins our knowledge and information about the role of forests in mitigating climate change. The availability of satellite-based AGB and AGB change (ΔAGB) products has increased in recent years. Here we assessed the past decade net ΔAGB derived from four recent global multi-date AGB maps: ESA-CCI maps, WRI-Flux model, JPL time series, and SMOS-LVOD time series. Our assessments explore and use different reference data sources with biomass re-measurements within the past decade. The reference data comprise National Forest Inventory (NFI) plot data, local ΔAGB maps from airborne LiDAR, and selected Forest Resource Assessment country data from countries with well-developed monitoring capacities. Map to reference data comparisons were performed at levels ranging from 100 m to 25 km spatial scale. The comparisons revealed that LiDAR data compared most reasonably with the maps, while the comparisons using NFI only showed some agreements at aggregation levels <10 km. Regardless of the aggregation level, AGB losses and gains according to the map comparisons were consistently smaller than the reference data. Map-map comparisons at 25 km highlighted that the maps consistently captured AGB losses in known deforestation hotspots. The comparisons also identified several carbon sink regions consistently detected by all maps. However, disagreement between maps is still large in key forest regions such as the Amazon basin. The overall ΔAGB map cross-correlation between maps varied in the range 0.11–0.29 (r). Reported ΔAGB magnitudes were largest in the high-resolution datasets including the CCI map differencing (stock change) and Flux model (gain-loss) methods, while they were smallest according to the coarser-resolution LVOD and JPL time series products, especially for AGB gains. Our results suggest that ΔAGB assessed from current maps can be biased and any use of the estimates should take that into account. Currently, ΔAGB reference data are sparse especially in the tropics but that deficit can be alleviated by upcoming LiDAR data networks in the context of Supersites and GEO-Trees.
|
|
4. |
- Ardö, Jonas, et al.
(author)
-
MODIS EVI-based net primary production in the Sahel 2000–2014
- 2018
-
In: International Journal of Applied Earth Observation and Geoinformation. - : Elsevier BV. - 1569-8432. ; 65, s. 35-45
-
Journal article (peer-reviewed)abstract
- Africa is facing resource problems due to increasing demand combined with potential climate-induced changes in supply. Here we aim to quantify resources in terms of net primary production (NPP [g C m−2 yr−1]) of vegetation in the Sahel region for 2000–2014.Using time series of the enhanced vegetation index (EVI) from MODIS, NPP was estimated for the Sahel region with a 500 × 500 m spatial resolution and 8-day temporal resolution. The estimates were based on local eddy covariance flux measurements from six sites in the Sahel region and the carbon use efficiency originating from a dynamic vegetation model.No significant NPP change was found for the Sahel as a region but, for sub-regions, significant changes, both increasing and decreasing, were observed. Substantial uncertainties related to NPP estimates and the small availability of evaluation data makes verification difficult. The simplicity of the methodology used, dependent on earth observation only, is considered an advantage.
|
|
5. |
- Axelsson, Arvid, et al.
(author)
-
Tree species classification using Sentinel-2 imagery and Bayesian inference
- 2021
-
In: International Journal of Applied Earth Observation and Geoinformation. - : Elsevier BV. - 1569-8432 .- 0303-2434. ; 100
-
Journal article (peer-reviewed)abstract
- The increased temporal frequency of optical satellite data acquisitions provides a data stream that has the potential to improve land cover mapping, including mapping of tree species. However, for large area operational mapping, partial cloud cover and different image extents can pose challenges. Therefore, methods are needed to assimilate new images in a straightforward way without requiring a total spatial coverage for each new image. This study shows that Bayesian inference applied sequentially has the potential to solve this problem. To test Bayesian inference for tree species classification in the boreo-nemoral zone of southern Sweden, field data from the study area of Remningstorp (58°27′18.35″ N, 13°39′8.03″ E) were used. By updating class likelihood with an increasing number of combined Sentinel-2 images, a higher and more stable cross-validated overall accuracy was achieved. Based on a Mahalanobis distance, 23 images were automatically chosen from the period of 2016 to 2018 (from 142 images total). An overall accuracy of 87% (a Cohen’s kappa of 78.5%) was obtained for four tree species classes: Betula spp., Picea abies, Pinus sylvestris, and Quercus robur. This application of Bayesian inference in a boreo-nemoral forest suggests that it is a practical way to provide a high and stable classification accuracy. The method could be applied where data are not always complete for all areas. Furthermore, the method requires less reference data than if all images were used for classification simultaneously.
|
|
6. |
- Axelsson, Christoffer, et al.
(author)
-
The use of dual-wavelength airborne laser scanning for estimating tree species composition and species-specific stem volumes in a boreal forest
- 2023
-
In: International Journal of Applied Earth Observation and Geoinformation. - : Elsevier BV. - 1569-8432 .- 1872-826X. ; 118
-
Journal article (peer-reviewed)abstract
- The estimation of species composition and species-specific stem volumes are critical components of many forest inventories. The use of airborne laser scanning with multiple spectral channels may prove instrumental for the cost-efficient retrieval of these forest variables. In this study, we scanned a boreal forest using two channels: 532 nm (green) and 1064 nm (near infrared). The data was used in a two-step methodology to (1) classify species, and (2) estimate species-specific stem volume at the level of individual tree crowns. The classification of pines, spruces and broadleaves involved linear discriminant analysis (LDA) and resulted in an overall accuracy of 91.1 % at the level of individual trees. For the estimation of stem volume, we employed species-specific k-nearest neighbors models and evaluated the performance at the plot level for 256 field plots located in central Sweden. This resulted in root-mean-square errors (RMSE) of 36 m3/ha (16 %) for total volume, 40 m3/ha (27 %) for pine volume, 32 m3/ha (48 %) for spruce volume, and 13 m3/ha (87 %) for broadleaf volume. We also simulated the use of a monospectral near infrared (NIR) scanner by excluding features based on the green channel. This resulted in lower overall accuracy for the species classification (86.8 %) and an RMSE of 41 m3/ha (18 %) for the estimation of total stem volume. The largest difference when only the NIR channel was used was the difficulty to accurately identify broadleaves and estimate broadleaf stem volume. When excluding the green channel, RMSE for broadleaved volume increased from 13 to 26 m3/ha. The study thus demonstrates the added benefit of the green channel for the estimation of both species composition and species-specific stem volumes. In addition, we investigated how tree height influences the results where shorter trees were found to be more difficult to classify correctly.
|
|
7. |
|
|
8. |
- Bhardwaj, Anshuman, et al.
(author)
-
A review on remotely sensed land surface temperature anomaly as an earthquake precursor
- 2017
-
In: International Journal of Applied Earth Observation and Geoinformation. - : Elsevier. - 1569-8432 .- 1872-826X. ; 63, s. 158-166
-
Journal article (peer-reviewed)abstract
- The low predictability of earthquakes and the high uncertainty associated with their forecasts make earthquakes one of the worst natural calamities, capable of causing instant loss of life and property. Here, we discuss the studies reporting the observed anomalies in the satellite-derived Land Surface Temperature (LST) before an earthquake. We compile the conclusions of these studies and evaluate the use of remotely sensed LST anomalies as precursors of earthquakes. The arrival times and the amplitudes of the anomalies vary widely, thus making it difficult to consider them as universal markers to issue earthquake warnings. Based on the randomness in the observations of these precursors, we support employing a global-scale monitoring system to detect statistically robust anomalous geophysical signals prior to earthquakes before considering them as definite precursors.
|
|
9. |
|
|
10. |
- Bohlin, Inka, et al.
(author)
-
Quantifying post-fire fallen trees using multi-temporal lidar
- 2017
-
In: International Journal of Applied Earth Observation and Geoinformation. - : Elsevier BV. - 0303-2434 .- 1569-8432. ; 63, s. 186-195
-
Journal article (peer-reviewed)abstract
- Massive tree-felling due to root damage is a common fire effect on burnt areas in Scandinavia, but has so far not been analyzed in detail. Here we explore if pre- and post-fire lidar data can be used to estimate the proportion of fallen trees. The study was carried out within a large (14,000 ha) area in central Sweden burnt in August 2014, where we had access to airborne lidar data from both 2011 and 2015. Three data-sets of predictor variables were tested: POST (post-fire lidar metrics), D1F (difference between post- and pre-fire lidar metrics) and combination of those two (POST_DIF). Fractional logistic regression was used to predict the proportion of fallen trees. Training data consisted of 61 plots, where the number of fallen and standing trees was calculated both in the field and with interpretation of drone images. The accuracy of the best model was tested based on 100 randomly selected validation plots with a size of 25 x 25 m.Our results showed that multi-temporal lidar together with field-collected training data can be used for quantifying post-fire tree felling over large areas. Several height-, density- and intensity metrics correlated with the proportion of fallen trees. The best model combined metrics from both datasets (POST DIF), resulting in a RMSE of 0.11. Results were slightly poorer in the validation plots with RMSE of 0.18 using pixel size of 12.5 m and RMSE of 0.15 using pixel size of 6.25 m. Our model performed least well for stands that had been exposed to high-intensity crown fire. This was likely due to the low amount of echoes from the standing black tree skeletons. Wall-to-wall maps produced with this model can be used for landscape level analysis of fire effects and to explore the relationship between fallen trees and forest structure, soil type, fire intensity or topography.
|
|