Creating a national baseline for natural resources, such as mangrove forests, and monitoring them regularly often requires a consistent and robust methodology. With freely available satellite data archives and cloud computing resources, it is now more accessible to conduct such large-scale monitoring and assessment. Yet, few studies examine the reproducibility of such mangrove monitoring frameworks, especially in terms of generating consistent spatial extent. Our objective was to evaluate a combination of image processing approaches to classify mangrove forests along the coast of Senegal and The Gambia. We used freely available global satellite data (Sentinel-2), and cloud computing platform (Google Earth Engine) to run two machine learning algorithms, random forest (RF), and classification and regression trees (CART). We calibrated and validated the algorithms using 800 reference points collected using high-resolution images. We further re-ran 10 iterations for each algorithm, utilizing unique subsets of the initial training data. While all iterations resulted in thematic mangrove maps with over 90% accuracy, the mangrove extent ranges between 827–2807 km² for Senegal and 245–1271 km² for The Gambia with one outlier for each country. We further report “Places of Agreement” (PoA) to identify areas where all iterations for both methods agree (506.6 km² and 129.6 km² for Senegal and The Gambia, respectively), thus have a high confidence in predicting mangrove extent. While we acknowledge the time- and cost-effectiveness of such methods for the landscape managers, we recommend utilizing them with utmost caution, as well as post-classification on-the-ground checks, especially for decision making.

Coastal mangrove forests provide important ecosystem goods and services, including carbon sequestration, biodiversity conservation, and hazard mitigation. However, they are being destroyed at an alarming rate by human activities. To characterize mangrove forest changes, evaluate their impacts, and support relevant protection and restoration decision making, accurate and up-to-date mangrove extent mapping at large spatial scales is essential. Available large-scale mangrove extent data products use a single machine learning method commonly with 30 m Landsat imagery, and significant inconsistencies remain among these data products. With huge amounts of satellite data involved and the heterogeneity of land surface characteristics across large geographic areas, finding the most suitable method for large-scale high-resolution mangrove mapping is a challenge. The objective of this study is to evaluate the performance of a machine learning ensemble for mangrove forest mapping at 20 m spatial resolution across West Africa using Sentinel-2 (optical) and Sentinel-1 (radar) imagery. The machine learning ensemble integrates three commonly used machine learning methods in land cover and land use mapping, including Random Forest (RF), Gradient Boosting Machine (GBM), and Neural Network (NN). The cloud-based big geospatial data processing platform Google Earth Engine (GEE) was used for pre-processing Sentinel-2 and Sentinel-1 data. Extensive validation has demonstrated that the machine learning ensemble can generate mangrove extent maps at high accuracies for all study regions in West Africa (92%–99% Producer’s Accuracy, 98%–100% User’s Accuracy, 95%–99% Overall Accuracy). This is the first-time that mangrove extent has been mapped at a 20 m spatial resolution across West Africa. The machine learning ensemble has the potential to be applied to other regions of the world and is therefore capable of producing high-resolution mangrove extent maps at global scales periodically.

As high-throughput biological sequencing becomes faster and cheaper, the need to extract useful information from sequencing becomes ever more paramount, often limited by low-throughput experimental characterizations. For proteins, accurate prediction of their functions directly from their primary amino-acid sequences has been a long standing challenge. Here, machine learning using artificial recurrent neural networks (RNN) was applied towards classification of protein function directly from primary sequence without sequence alignment, heuristic scoring or feature engineering. The RNN models containing long-short-term-memory (LSTM) units trained on public, annotated datasets from UniProt achieved high performance for in-class prediction of four important protein functions tested, particularly compared to other machine learning algorithms using sequence-derived protein features. RNN models were used also for out-of-class predictions of phylogenetically distinct protein families with similar functions, including proteins of the CRISPR-associated nuclease, ferritin-like iron storage and cytochrome P450 families. Applying the trained RNN models on the partially unannotated UniRef100 database predicted not only candidates validated by existing annotations but also currently unannotated sequences. Some RNN predictions for the ferritin-like iron sequestering function were experimentally validated, even though their sequences differ significantly from known, characterized proteins and from each other and cannot be easily predicted using popular bioinformatics methods. As sequencing and experimental characterization data increases rapidly, the machine-learning approach based on RNN could be useful for discovery and prediction of homologues for a wide range of protein functions.

The acyl carrier protein (ACP) is an essential and ubiquitous component of microbial synthesis of fatty acids, the natural precursor to biofuels. Natural fatty acids usually contain long chains of 16 or more carbon atoms. Shorter carbon chains, with increased fuel volatility, are desired for internal combustion engines. Engineering the length specificity of key proteins in fatty acid metabolism, such as ACP, may enable microbial synthesis of these shorter chain fatty acids. We constructed a homology model of the Synechococcus elongatus ACP, showing a hydrophobic pocket harboring the growing acyl chain. Amino acids within the pocket were mutated to increase steric hindrance to the acyl chain. Certain mutant ACPs, when over-expressed in Escherichia coli, increased the proportion of shorter chain lipids; I75 W and I75Y showed the strongest effects. Expression of I75 W and I75Y mutant ACPs also increased production of lauric acid in E. coli that expressed the C12-specific acyl-ACP thioesterase from Cuphea palustris. We engineered the specificity of the ACP, an essential protein of fatty acid metabolism, to alter the E. coli lipid pool and enhance production of medium-chain fatty acids as biofuel precursors. These results indicate that modification of ACP itself could be combined with enzymes affecting length specificity in fatty acid synthesis to enhance production of commodity chemicals based on fatty acids.

The United Nations Sustainable Development Goals (SDGs) include 17 interlinked goals designed to be a blueprint for the world’s nations to achieve a better and more sustainable future, and the specific SDG 3 is a public health–related goal to ensure healthy living and promote well-being for all population groups. To facilitate SDG planning, implementation, and progress monitoring, many SDG indicators have been developed. Based on the United Nations General Assembly resolutions, SDG indicators need to be disaggregated by geographic locations and thematic environmental and socioeconomic characteristics for achieving the most accurate planning and progress assessment. High-resolution data such as those captured at the village level can provide comparatively more precise insights into the different socioeconomic and environmental factors relevant to SDGs, therefore enabling more effective sustainable development decision-making. Using India as our study area and the child malnutrition indicators stunting, underweight, and wasting as examples of public health–related SDG indicators, we have demonstrated a process to effectively derive environmental variables at the village level from satellite big datasets on a cloud platform for SDG research and applications. Spatial analysis of environmental variables regarding vegetation, climate, and terrain have shown spatial grouping patterns across the entire study area, with each village group having different statistics. Correlation analysis between these environmental variables and stunting, underweight, and wasting indicators show a meaningful relationship between these indicators and vegetation index, land surface temperature, rainfall, elevation, and slope. Identifying the spatial variation patterns of environmental variables at the village level and their correlations with child malnutrition indicators can be an invaluable tool to facilitate a clearer understanding of the causes of child malnutrition and to improve area-specific SDG 3 implementation planning. This analysis can also provide meaningful support in assessing and monitoring SDG implementation progress at the village level by spatially predicting SDG indicators using available socioeconomic and environmental independent variables. The methodology used in this study has the potential to be applied to other similar regions, especially low-to-middle income countries where a high number of children are severely affected by malnutrition, as well as to other environmentally related SDGs, such as Goal 1 (No Poverty) and Goal 2 (Zero Hunger).