The characterization of carbon stocks and dynamics at the national level is critical for countries engaging in climate change mitigation and adaptation strategies. However, several tropical countries, including Kenya, lack the essential information typically provided by a complete national forest inventory. Here we present the most detailed and rigorous national-scale assessment of aboveground woody biomass carbon stocks and dynamics for Kenya to date. A non-parametric random forest algorithm was trained to retrieve aboveground woody biomass carbon (AGBC) for the year 2014 ± 1 and forest disturbances for the 2014–2017 period using in situ forest inventory plot data and satellite Earth Observation (EO) data. The ecosystem carbon cycling of Kenya’s forests and wooded grassland were assessed using a model-data fusion framework, CARDAMOM, constrained by the woody biomass datasets from this study as well as time series information on leaf area, fire events and soil organic carbon. Our EO-derived AGBC stocks were estimated as 140 Mt C for forests and 199 Mt C for wooded grasslands. The total AGBC loss during the study period was estimated as 1.89 Mt C with a dispersion below 1%. The CARDAMOM analysis estimated woody productivity to be three times larger in forests (mean = 1.9 t C ha−1 yr−1) than wooded grasslands (0.6 t C ha−1 yr−1), and the mean residence time of woody C in forests (16 years) to be greater than in wooded grasslands (10 years). This study stresses the importance of carbon sequestration by forests in the international climate mitigation efforts under the Paris Agreement, but emphasizes the need to include non-forest ecosystems such as wooded grasslands in international greenhouse gas accounting frameworks.

The successful application of deep learning approaches in remote sensing image classification requires large hyperspectral image (HSI) datasets to learn discriminative spectral–spatial features simultaneously. To date, the HSI datasets available for image classification are relatively small to train deep learning methods. This study proposes a deep 3D/2D genome graph-based network (abbreviated as HybridGBN-SR) that is computationally efficient and not prone to overfitting even with extremely few training sample data. At the feature extraction level, the HybridGBN-SR utilizes the three-dimensional (3D) and two-dimensional (2D) Genoblocks trained using very few samples while improving HSI classification accuracy. The design of a Genoblock is based on a biological genome graph. From the experimental results, the study shows that our model achieves better classification accuracy than the compared state-of-the-art methods over the three publicly available HSI benchmarking datasets such as the Indian Pines (IP), the University of Pavia (UP), and the Salinas Scene (SA). For instance, using only 5% labeled data for training in IP, and 1% in UP and SA, the overall classification accuracy of the proposed HybridGBN-SR is 97.42%, 97.85%, and 99.34%, respectively, which is better than the compared state-of-the-art methods.

Recently developed hybrid models that stack 3D with 2D CNN in their structure have enjoyed high popularity due to their appealing performance in hyperspectral image classification tasks. On the other hand, biological genome graphs have demonstrated their effectiveness in enhancing the scalability and accuracy of genomic analysis. We propose an innovative deep genome graph-based network (GGBN) for hyperspectral image classification to tap the potential of hybrid models and genome graphs. The GGBN model utilizes 3D-CNN at the bottom layers and 2D-CNNs at the top layers to process spectral–spatial features vital to enhancing the scalability and accuracy of hyperspectral image classification. To verify the effectiveness of the GGBN model, we conducted classification experiments on Indian Pines (IP), University of Pavia (UP), and Salinas Scene (SA) datasets. Using only 5% of the labeled data for training over the SA, IP, and UP datasets, the classification accuracy of GGBN is 99.97%, 96.85%, and 99.74%, respectively, which is better than the compared state-of-the-art methods.

No abstract

Developing complex hyperspectral image (HSI) sensors that capture high-resolution spatial information and voluminous (hundreds) spectral bands of the earth’s surface has made HSI pixel-wise classification a reality. The 3D-CNN has become the preferred HSI pixel-wise classification approach because of its ability to extract discriminative spectral and spatial information while maintaining data integrity. However, HSI datasets are characterized by high nonlinearity, voluminous spectral features, and limited training sample data. Therefore, developing deep HSI classification methods that purely utilize 3D-CNNs in their network structure often results in computationally expensive models prone to overfitting when the model depth increases. In this regard, this paper proposes an integrated deep multi-scale 3D/2D convolutional network block (MiCB) for simultaneous low-level spectral and high-level spatial feature extraction, which can optimally train on limited sample data. The strength of the proposed MiCB model solely lies in the innovative arrangement of convolution layers, giving the network the ability (i) to simultaneously convolve the low-level spectral with high-level spatial features; (ii) to use multiscale kernels to extract abundant contextual information; (iii) to apply residual connections to solve the degradation problem when the model depth increases beyond the threshold; and (iv) to utilize depthwise separable convolutions in its network structure to address the computational cost of the proposed MiCB model. We evaluate the efficacy of our proposed MiCB model using three publicly accessible HSI benchmarking datasets: Salinas Scene (SA), Indian Pines (IP), and the University of Pavia (UP). When trained on small amounts of training sample data, MiCB is better at classifying than the state-of-the-art methods used for comparison. For instance, the MiCB achieves a high overall classification accuracy of 97.35%, 98.29%, and 99.20% when trained on 5% IP, 1% UP, and 1% SA data, respectively.