Spatially and temporally consistent vegetation structure time-series have great potential to improve the capacity for national land cover monitoring, to reduce latency and cost of international reporting, and to harmonize regional land cover characterizations. Here we present a semi-automatic, operational algorithm for mapping and monitoring of woody vegetation canopy cover and height at a regional scale using freely available Landsat time-series data. The presented algorithm employs automatic data processing and mapping using a set of lidar-based vegetation structure prediction models. Changes in vegetation cover are detected separately and integrated into the structure time-series. Sample-based validation and inter-comparison with existing datasets demonstrates the spatial and temporal consistency of our regional data time-series. The dataset reliably reflects changes in tree cover (tree cover loss user's accuracy of 0.84 and producer's accuracy of 0.75) and can serve as a tool to map annual forest extent (user's accuracy of 0.98 and producer's accuracy of 0.81 for 10% canopy cover threshold to define the forest class). The tree height estimates are consistent with a GLAS-based global map (mean average error of 3.7 m, the correlation coefficient of 0.92 and the R2 of 0.85). The algorithm was prototyped within the Lower Mekong region where it revealed an intensive woody vegetation dynamic. Of the year 2000 forest area (defined using canopy cover threshold of 10% and tree height threshold of 5 m), 9.4% was deforested by the year 2017, and 16.6% was affected by stand-replacement disturbance followed by reforestation. The average annual area of stand-level forest disturbance within the region was 2.34 Mha, and increased by 34% from 2001 (1.85 Mha) to 2017 (2.48 Mha). Total forest area decreased by 6.2% within the region, and 11.1% of year 2000 primary forest area was lost by 2017. At the national level, Cambodia demonstrated the highest rate of deforestation, with a net forest area loss of 22.5%. We estimated that 21.3% of 2017 forest cover had an age of 17 years or less, illustrating the intensive forest land uses within the region. The time-series product is suitable for mapping annual land cover and inter-annual land cover change using customized class definitions. The regionally-consistent data are publicly available for download (https://glad.umd.edu/), and online analysis (https://rlcms-servir.adpc.net/en/forest-monitor/), and serve as an input to the SERVIR-Mekong Regional Land Cover Monitoring System.
Bhandari et al., (2024). servir-aces: A Python Package for Training Machine Learning Models for Remote Sensing Applications. Journal of Open Source Software, 9(99), 6729, https://doi.org/10.21105/joss.06729
Land cover change and its impact on food security is a topic that has major implications for development in population-dense Southeast Asia. The main drivers of forest loss include the expansion of agriculture and plantation estates, growth of urban centers, extraction of natural resources, and water infrastructure development. The design and implementation of appropriate land use policies requires accurate and timely information on land cover dynamics to account for potential political, economical, and agricultural consequences. Therefore, SERVIR-Mekong led the collaborative development of a Regional Land Cover Monitoring System (RLCMS) with key regional stakeholders across the greater Mekong region. Through this effort, a modular system was used to create yearly land cover maps for the period 1988 - 2017. In this study, we compared this 30-year land cover time-series with Viet Nam national forest resources and agricultural productivity statistics. We used remote sensing-derived land cover products to quantify landscape changes and linked those with food availability, one of food security dimension, from a landscape approach perspective. We found that agricultural production has soared while the coverage of agricultural areas has remained relatively stable. Land cover change dynamics coincide with important legislation regarding environmental management and sustainable development strategies in Viet Nam. Our findings indicate that Vietnam has made major steps towards improving its' food security. We demonstrate that RLCMS is a valuable tool for evaluating the relationship between policies and their impacts on food security, ecosystem services and natural capital.
Creating annual crop type maps for enabling improved food security decision making has remained a challenge in Bhutan. This is in part due to the level of effort required for data collection, technical model development, and reliability of an on-the-ground application. Through focusing on advancing Science, Technology, Engineering, and Mathematics (STEM) in Bhutan, an effort to co-develop a geospatial application known as the Agricultural Classification and Estimation Service (ACES) was created. This paper focuses on the co-development of an Earth observation informed climate smart crop type framework which incorporates both modeling and training sample collection. The ACES web application and subsequent ACES modeling software package enables stakeholders to more readily use Earth observation into their decision making process. Additionally, this paper offers a transparent and replicable approach for addressing and combating remote sensing limitations due to topography and cloud cover, a common problem in Bhutan. Lastly, this approach resulted in a Random Forest “LTE 555” model, from a set of 3,600 possible models, with an overall test Accuracy of 85% and F-1 Score of .88 for 2020. The model was independently validated resulting in an independent accuracy of 83% and F-1 Score of .45 for 2020. The insight into the model perturbation via hyperparameter tuning and input features is key for future practitioners.
The International Telecommunication Union (ITU) Standardization Sector recommends implementing the ITU-T X.1303 Common Alerting Protocol (CAP) early warning standard [1].The Sahana Alerting and Messaging Broker (SAMBRO) software adopts CAP and similar policies and procedures recommended for Mexico by Christian [2].SAMBRO was operationalized in Myanmar, Maldives, and the Philippines.The strategies for implementing CAP, customizing SAMBRO, and incorporating Information Communication Technologies (ICTs) to meet the individual country requirements, are the primary discussion in this paper.This informative paper presents itself as a case study for CAP Practitioners and Researchers to make use in improving warning interoperability.
<p>Floods and water-related disasters impact local populations across many regions in Southeast Asia during the annual monsoon season.&#160; Satellite remote sensing serves as a critical resource for generating flood maps used in disaster efforts to evaluate flood extent and monitor recovery in remote and isolated regions where information is limited.&#160; However, these data are retrieved by multiple sensors, have varying latencies, spatial, temporal, and radiometric resolutions, are distributed in different formats, and require different processing methods making it difficult for end-users to use the data.&#160; SERVIR-Mekong has developed a near real-time flood service, HYDRAFloods, in partnership with Myanmar&#8217;s Department of Disaster Management that leverages Google Earth Engine and cloud computing to generate automated multi-sensor flood maps using the most recent imagery available of affected areas. The HYDRAFloods application increases the spatiotemporal monitoring of hydrologic events across large areas by leveraging optical, SAR, and microwave remote sensing data to generate flood water extent maps.&#160; Beta testing of HYDRFloods conducted during the 2019 Southeast Asia monsoon season emphasized the importance of multi-sensor observations as frequent cloud cover limited useable imagery for flood event monitoring. Given HYDRAFloods&#8217; multi-sensor approach, cloud-based resources offer a means to consolidate and streamline the process of accessing, processing, and visualizing flood maps in a more cost effective and computationally efficient way. The HYDRAFlood&#8217;s cloud-based approach enables a consistent, automated methodology for generating flood extent maps that are made available through a single, tailored, mapviewer that has been customized based on end-user feedback, allowing users to switch their focus to using data for disaster response.</p>
In this study, we develop a vegetation monitoring framework which is applicable at a planetary scale, and is based on the BACI (Before-After, Control-Impact) design. This approach utilizes Google Earth Engine, a state-of-the-art cloud computing platform. A web-based application for users named EcoDash was developed. EcoDash maps vegetation using Enhanced Vegetation Index (EVI) from Moderate Resolution Imaging Spectroradiometer (MODIS) products (the MOD13A1 and MYD13A1 collections) from both Terra and Aqua sensors from the years 2000 and 2002, respectively. to detect change in vegetation, we define an EVI baseline period, and then draw results at a planetary scale using the web-based application by measuring improvement or degradation in vegetation based on the user-defined baseline periods. We also used EcoDash to measure the impact of deforestation and mitigation efforts by the Vietnam Forests and Deltas (VFD) program for the Nghe An and Thanh Hoa provinces in Vietnam. Using the period before 2012 as a baseline, we found that as of March 2017, 86% of the geographical area within the VFD program shows improvement, compared to only a 24% improvement in forest cover for all of Vietnam. Overall, we show how using satellite imagery for monitoring vegetation in a cloud-computing environment could be a cost-effective and useful tool for land managers and other practitioners
Maldives, Myanmar, and the Philippines are vulnerable to natural disasters. Sendai Framework of Action calls for risk reduction by implementing early warning systems. A prevailing challenge is for authorities to coordinate warnings across disparate communication systems and autonomous organizations. Cross-Agency Situational-Awareness platforms and the ITU-T X.1303 Common Alerting Protocol (CAP) interoperable data standards presents themselves as solution for diluting the inter-agency rivalries and interconnection disparities. The CAP-enabled Sahana Alerting and Messaging Broker (SAMBRO) was designed to overcome these issues by providing a Common Operating Picture and a platform for all Stakeholders to share and disseminate early warnings. To that end, the CAP-on-a-MAP project implemented SAMBRO and the CAP standard along with the policies and procedures, recommended by Christian (2016) in the three countries. The project evaluated the usability and acceptability of the intervention through a ‘gulf of evaluation’ complexity analysis method and by applying the ‘technology acceptance model’. The users ‘agreed’ that SAMBRO was ‘useful’ and ‘easy to use’. Moreover, they had ‘quite’ a good attitude towards adopting and indicated that it was beneficial. This paper discusses the outcomes of the evaluation and the policy implications that would allow for sustaining and scaling the concept of cross-agency situational-awareness for improving institutional responsiveness to coastal-hazards in the three countries.
 scale(5.56106)'%3e%3ccircle r='1'/%3e%3cg id='d'%3e%3cg id='c'%3e%3cpath id='b' d='M.195-.98 0-1.39l-.195.408' transform='rotate(11.25)'/%3e%3cuse xlink:href='%23b' transform='rotate(22.5)'/%3e%3cuse xlink:href='%23b' transform='rotate(45)'/%3e%3c/g%3e%3cuse xlink:href='%23c' transform='rotate(67.5)'/%3e%3c/g%3e%3cuse xlink:href='%23d' transform='scale(-1 1)'/%3e%3c/g%3e%3cg transform='translate(0 58.787) scale(8.1434)'%3e%3ccircle r='1'/%3e%3cg id='g'%3e%3cg id='f'%3e%3cpath id='e' d='M.259.966 0 1.576l-.259-.61'/%3e%3cuse xlink:href='%23e' transform='rotate(180)'/%3e%3c/g%3e%3cuse xlink:href='%23f' transform='rotate(90)'/%3e%3c/g%3e%3cuse xlink:href='%23g' transform='rotate(30)'/%3e%3cuse xlink:href='%23g' transform='rotate(60)'/%3e%3c/g%3e%3c/g%3e%3c/svg%3e)
