Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Environmental changes”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,387 records · Page 77

Biological and Environmental Research, Climate and Environmental Sciences Division: U.S./European Workshop on Climate Change Challenges and Observations

The workshop aimed to identify outstanding climate change science questions and the observational strategies for addressing them. The scientific focus was clouds, aerosols, and precipitation, and the required ground- and aerial-based observations. The workshop findings will be useful input for setting priorities within the Department of Energy (DOE) and the participating European centers. This joint workshop was envisioned as the first step in enhancing the collaboration among these climate research activities needed to better serve the science community.

54 ENVIRONMENTAL SCIENCES↗

What goes on behind closed doors? How college dormitory residents change to save energy during a competition-based energy reduction intervention

Here, the aim of our study was to evaluate the impact of a competition-based intervention combining high resolution electricity feedback, incentives, information, and prompts on college dormitory residents’ energy consumption and participation in demand response (DR) events. We also investigated changes in individual-level pro-environmental behaviors and examined psycho-social correlates of behavior change. Residents of 39 suites in a freshman residence hall competed against one another to reduce energy consumption and win prizes as part of a 3-week competition. Feedback was provided in near real time at the suite-level via an interactive touch-screen kiosk. Participants also completed baseline and followup surveys. Findings have indicated that electricity use among all suites was approximately 6.4% lower during the competition period compared to baseline, a significant reduction. Additionally, participants reported engaging in various pro-environmental behaviors significantly more frequently during the competition relative to baseline. Changes in pro-environmental behavior were associated with changes in level of group identification and perceived social norms. In three weeks, dormitory residents saved 3, 158 kWh of electricity compared to baseline – the equivalent of more than 3, 470 pounds of carbon dioxide emissions. Our findings provide evidence that real-time feedback, combined with incentives, information, and prompts, can motivate on-campus residents to reduce energy consumption. We contribute to a limited body of evidence supporting the effectiveness of dorm energy competitions in motivating college students to save energy. In addition, we identified individual-level behavioral and psycho-social changes made during such an intervention. University residential life planners may also use the results of this research to inform student programming.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Optimizing Deep Learning Models for Climate-Related Natural Disaster Detection from UAV Images and Remote Sensing Data

This research study utilized artificial intelligence (AI) to detect natural disasters from aerial images. Flooding and desertification were two natural disasters taken into consideration. The Climate Change Dataset was created by compiling various open-access data sources. This dataset contains 6334 aerial images from UAV (unmanned aerial vehicles) images and satellite images. The Climate Change Dataset was then used to train Deep Learning (DL) models to identify natural disasters. Four different Machine Learning (ML) models were used: convolutional neural network (CNN), DenseNet201, VGG16, and ResNet50. These ML models were trained on our Climate Change Dataset so that their performance could be compared. DenseNet201 was chosen for optimization. All four ML models performed well. DenseNet201 and ResNet50 achieved the highest testing accuracies of 99.37% and 99.21%, respectively. This research project demonstrates the potential of AI to address environmental challenges, such as climate change-related natural disasters. This study’s approach is novel by creating a new dataset, optimizing an ML model, cross-validating, and presenting desertification as one of our natural disasters for DL detection. Three categories were used (Flooded, Desert, Neither). Our study relates to AI for Climate Change and Environmental Sustainability. Drone emergency response would be a practical application for our research project.

AI↗

Fast response of fungal and prokaryotic communities to climate change manipulation in two contrasting tundra soils

Climate models predict substantial changes in temperature and precipitation patterns across Arctic regions, including increased winter precipitation as snow in the near future. Soil microorganisms are considered key players in organic matter decomposition and regulation of biogeochemical cycles. However, current knowledge regarding their response to future climate changes is limited. Here, we explore the short-term effect of increased snow cover on soil fungal, bacterial and archaeal communities in two tundra sites with contrasting water regimes in Greenland. In order to assess seasonal variation of microbial communities, we collected soil samples four times during the plant-growing season. The analysis revealed that soil microbial communities from two tundra sites differed from each other due to contrasting soil chemical properties. Fungal communities showed higher richness at the dry site whereas richness of prokaryotes was higher at the wet tundra site. We demonstrated that fungal and bacterial communities at both sites were significantly affected by short-term increased snow cover manipulation. Our results showed that fungal community composition was more affected by deeper snow cover compared to prokaryotes. The fungal communities showed changes in both taxonomic and ecological groups in response to climate manipulation. However, the changes were not pronounced at all sampling times which points to the need of multiple sampling in ecosystems where environmental factors show seasonal variation. Further, we showed that effects of increased snow cover were manifested after snow had melted. We demonstrated rapid response of soil fungal and bacterial communities to short-term climate manipulation simulating increased winter precipitation at two tundra sites. In particular, we provide evidence that fungal community composition was more affected by increased snow cover compared to prokaryotes indicating fast adaptability to changing environmental conditions. Since fungi are considered the main decomposers of complex organic matter in terrestrial ecosystems, the stronger response of fungal communities may have implications for organic matter turnover in tundra soils under future climate.

54 ENVIRONMENTAL SCIENCES↗

Functional metabolomics: from biomarker discovery to metabolome reprogramming

Metabolomics is emerging as a powerful tool for studying metabolic processes, identifying crucial biomarkers responsible for metabolic characteristics and revealing metabolic mechanisms, which construct the content of discovery metabolomics. The crucial biomarkers can be used to reprogram a metabolome, leading to an aimed metabolic strategy to cope with alteration of internal and external environments, naming reprogramming metabolomics here. The striking feature on the similarity of the basic metabolic pathways and components among vastly different species makes the reprogramming metabolomics possible when the engineered metabolites play biological roles in cellular activity as a substrate of enzymes and a regulator to other molecules including proteins. The reprogramming metabolomics approach can be used to clarify metabolic mechanisms of responding to changed internal and external environmental factors and to establish a framework to develop targeted tools for dealing with the changes such as controlling and/or preventing infection with pathogens and enhancing host immunity against pathogens. This review introduces the current state and trends of discovery metabolomics and reprogramming metabolomics and highlights the importance of reprogramming metabolomics.

reprogramming metabolomics↗

Identifying geologic characteristics and operational decisions to meet global carbon sequestration goals

Geologic carbon sequestration is the process of injecting and storing CO 2 in subsurface reservoirs and is an essential technology for global environmental security (e.g., climate change mitigation) and economic security (e.g., CO 2 tax credits). To meet energy, economic, and environmental goals, society will have to identify vast volumes of high-capacity, low-cost, and viable storage reservoirs for sequestering CO 2 . In turn, this requires understanding how major geologic characteristics (such as reservoir depth, thickness, permeability, porosity, and temperature) and design and operational decisions (such as injection well spacing) impact CO 2 injection rates, storage capacity, and economics. Although many numerical simulation tools exist, they cannot repeat the required thousands or millions of simulations to identify ideal reservoir properties and the sensitivity and interaction between geologic parameters and operational decisions. Here, we use SCO 2 T—a fast-running, reduced-order modeling framework—to explore the sensitivity of major geologic parameters and operational decisions to engineering (CO 2 injection rates, plume dimensions, and storage capacities and effectiveness) and costs. Our results show, for the first time, benefits and impacts such as allowing CO 2 plumes to overlap, how different well spacing patterns affect CO 2 sequestration, the effects on costs of including brine treatment and disposal, and the effect of restricting injection rates to 1 MtCO 2 per y based on well limitations. We reveal multiple novel and unintuitive findings including: (i) deeper reservoirs have reduced carbon sequestration costs until injection rates reach 1 MtCO 2 per y, at which point deeper reservoirs become more expensive, (ii) thicker formations allow for increased injection rates and storage capacity, but thickness barely impacts plume areas, (iii) higher geothermal gradients result in reduced sequestration costs, unless brine treatment/disposal costs are included, at which point reservoirs having lower geothermal gradients are more economical because they produce less brine for each unit of injected CO 2 , and (iv) allowing plumes to overlap has a significantly positive impact of increasing storage capacities but has only a small influence on reducing sequestration costs. Altogether, our results illustrate new scientific conclusions to help identify suitable sites to inject and store CO 2 , to help understand the complex interaction between geology and resulting costs, and to help support the pursuit of meeting global sequestration targets.

58 GEOSCIENCES↗

Thermoelectric air conditioning undergarment for personal thermal management and HVAC energy saving

Personal thermal management systems (PTMS) are highly desirable for improving individual thermal comfort and reducing indoor HVAC energy consumption. Although there have been many attempts in developing PTMS, existing PTMS are generally bulky, heavy or immobile. Besides, previous analysis on additional personal cooling and heating power required for maintaining thermal comfort in changing environments did not consider the individual difference in metabolism and the variability of comfort skin temperature with environmental conditions. In this paper, we report on the development of a novel lightweight (<1 kg) thermoelectric air conditioning undergarment system with a preferred design of branching tubing network (branching angle of 60° and diameter ratio of 0.782) for air distribution. Through thermal manikin and human subject tests, we demonstrated that the novel system is capable of providing a maximum of 15.5 W of personal cooling and 18.1 W personal heating with a coefficient of performance (COP) greater than 0.4, which is sufficient to the expansion of the indoor set-points by at least 2.2 °C (4 °F) on both sides without compromising thermal comfort and the potential saving of about 15% HVAC energy. Furthermore, our study improved the understanding of the required additional personal cooling and heating power for changing environmental conditions, which are essential guidelines for the further development of PTMS.

42 ENGINEERING↗

The impact of climate change and emissions control on future ozone levels: Implications for human health

Overwhelming evidence has shown that, from the Industrial Revolution to the present, human activities influence ground-level ozone (O 3 ) concentrations. Past studies demonstrate links between O 3 exposure and health. However, knowledge gaps remain in our understanding concerning the impacts of climate change mitigation policies on O 3 concentrations and health. Using a hybrid downscaling approach, we evaluated the separate impact of climate change and emission control policies on O 3 levels and associated excess mortality in the US in the 2050s under two Representative Concentration Pathways (RCPs). We show that, by the 2050s, under RCP4.5, increased O 3 levels due to combined climate change and emission control policies, could contribute to an increase of approximately 50 premature deaths annually nationwide in the US. The biggest impact, however, is seen under RCP8.5, where rises in O 3 concentrations are expected to result in over 2,200 additional premature deaths annually. Here, the largest increases in O 3 are seen in RCP8.5 in the Northeast, the Southeast, the Central, and the West regions of the US. Additionally, when O 3 increases are examined by climate change and emissions contributions separately, the benefits of emissions mitigation efforts may significantly outweigh the effects of climate change mitigation policies on O 3 -related mortality.

54 ENVIRONMENTAL SCIENCES↗

Impact of Shifts in Vegetation Phenology on the Carbon Balance of a Semiarid Sagebrush Ecosystem

Dryland ecosystems are critical in regulating the interannual variability of the global terrestrial carbon cycle. The responses of such ecosystems to weather and environmental conditions remain important factors that limit the accurate projections of carbon balance under future climate change. Here, we investigated how shifts in vegetation phenology resulting from changes in weather and environmental conditions influenced ecosystem carbon cycling in one semiarid ecosystem in the Hanford area of central Washington, United States. We examined two years of measurements of the phenology camera, eddy covariance, and soil chamber from an upland semiarid sagebrush ecosystem. Both years had contrasting diel and seasonal patterns of CO 2 fluxes, primarily driven by differences in vegetation phenology. The net ecosystem exchange of CO 2 (NEE) and evapotranspiration (ET) in 2019 were enlarged by shifted vegetation phenology, as a cold and snow-covered winter and warm and dry winter in 2020 resulted in constrained magnitudes of NEE and ET during the summer months. The annual gross primary productivity (GPP) was much higher in 2019 than in 2020 (-211 vs. -112 gC m -2 ), whereas ecosystem respiration was comparable in these two years (164 vs. 144 gC m -2 ). Thus, the annual NEE in 2019 was negative (-47 gC m -2 ) with the sagebrush ecosystem functioning as a carbon sink, while the positive annual NEE in 2020 indicated that the sagebrush ecosystem functioned as a carbon source. Our results demonstrate that winter snowpack can be a critical driver of annual carbon uptake in semiarid sagebrush ecosystems.

59 BASIC BIOLOGICAL SCIENCES↗

Evaluating temporal controls on greenhouse gas (GHG) fluxes in an Arctic tundra environment: An entropy-based approach

We report that there is significant spatial and temporal variability associated with greenhouse gas (GHG) fluxes in high-latitude Arctic tundra environments. The objectives of this study are to investigate temporal variability in CO 2 and CH 4 fluxes at Barrow, AK and to determine the factors causing this variability using a novel entropy-based classification scheme. In particular, we analyzed which geomorphic, soil, vegetation and climatic properties most explained the variability in GHG fluxes (opaque chamber measurements) during the growing season over three successive years. Results indicate that multi-year variability in CO 2 fluxes was primarily associated with soil temperature variability as well as vegetation dynamics during the early and late growing season. Temporal variability in CH 4 fluxes was primarily associated with changes in vegetation during the growing season and its interactions with primary controls like seasonal thaw. Polygonal ground features, which are common to Arctic regions, also demonstrated significant multi-year variability in GHG fluxes. Our results can be used to prioritize field sampling strategies, with an emphasis on measurements collected at locations and times that explain the most variability in GHG fluxes. For example, we found that sampling primary environmental controls at the centers of high centered polygons in the month of September (when freeze-back period begins) can provide significant constraints on GHG flux variability – a requirement for accurately predicting future changes to GHG fluxes. In conclusion, entropy results document the impact of changing environmental conditions (e.g., warming, growing season length) on GHG fluxes, thus providing clues concerning the manner in which ecosystem properties may be shifted regionally in a future climate.

54 ENVIRONMENTAL SCIENCES↗

Fractals and Spatial Methods for Mining Remote Sensing Imagery

The rapid increase in digital remote sensing and GIS data raises a critical problem -- how can such an enormous amount of data be handled and analyzed so that useful information can be derived quickly? Efficient handling and analysis of large spatial data sets is central to environmental research, particularly in global change studies that employ time series. Advances in large-scale environmental monitoring and modeling require not only high-quality data, but also reliable tools to analyze the various types of data. A major difficulty facing geographers and environmental scientists in environmental assessment and monitoring is that spatial analytical tools are not easily accessible. Although many spatial techniques have been described recently in the literature, they are typically presented in an analytical form and are difficult to transform to a numerical algorithm. Moreover, these spatial techniques are not necessarily designed for remote sensing and GIS applications, and research must be conducted to examine their applicability and effectiveness in different types of environmental applications. This poses a chicken-and-egg problem: on one hand we need more research to examine the usability of the newer techniques and tools, yet on the other hand, this type of research is difficult to conduct if the tools to be explored are not accessible. Another problem that is fundamental to environmental research are issues related to spatial scale. The scale issue is especially acute in the context of global change studies because of the need to integrate remote-sensing and other spatial data that are collected at different scales and resolutions. Extrapolation of results across broad spatial scales remains the most difficult problem in global environmental research. There is a need for basic characterization of the effects of scale on image data, and the techniques used to measure these effects must be developed and implemented to allow for a multiple scale assessment of the data before any useful process-oriented modeling involving scale-dependent data can be conducted. Through the support of research grants from NASA, we have developed a software module called ICAMS (Image Characterization And Modeling System) to address the need to develop innovative spatial techniques and make them available to the broader scientific communities. ICAMS provides new spatial techniques, such as fractal analysis, geostatistical functions, and multiscale analysis that are not easily available in commercial GIS/image processing software. By bundling newer spatial methods in a user-friendly software module, researchers can begin to test and experiment with the new spatial analysis methods and they can gauge scale effects using a variety of remote sensing imagery. In the following, we describe briefly the development of ICAMS and present application examples.

Lam, Nina↗

Ohio River Basin Water Resources: Monitoring Flash Drought Potential and Quantifying the Hydrologic Impacts in the Ohio River Basin

Flash drought conditions emerge in a matter of weeks following persistent weather anomalies, such as high temperatures or large vapor pressure deficits, that drive increased evaporative demand. Vegetation response rapidly depletes soil moisture, threatening surface water supplies, triggering significant crop loss, and increasing wildfire risk. Drought indices sensitive to flash drought are currently not included in drought forecast models in the Ohio River Basin (ORB). The team assessed and compared drought indices, gauge-based data, and satellite measurements over the course of the September 2019 flash drought event in the Ohio River Basin to investigate environmental fingerprints throughout flash drought evolution. Potential leading flash drought indicators were compared to the Standardized Precipitation Index (SPI) to aid the National Weather Service (NWS) Ohio River Forecast Center and Kentucky Climate Center in producing early warning flash drought forecasts. These drought indices included Evaporative Demand Drought Index (EDDI), Standardized Precipitation Evapotranspiration Index (SPEI), and Landscape Evaporative Response Index (LERI) (derived from Terra Moderate Resolution Imaging Spectroradiometer (MODIS)). Drought index behavior inherently varies based on parameters incorporated - EDDI measures evaporative demand through potential evapotranspiration, and demonstrates more variations due to sensitivity to seasonal changes in evaporative demand throughout the 2010-2019 study period. Conversely, LERI measures evaporative response through actual evapotranspiration, representing different environmental changes. Soil moisture response was evaluated using Soil Moisture Active Passive (SMAP) L-band radiometer data and Kentucky Mesonet gauge-based measurements. This analysis enables climatologists and weather forecasters to keep decision-makers and stakeholders better informed about drought risks, and to implement the appropriate actions for preparation of drought onset.

Adelaide Schmid↗

A Systematic Evidence Based Performance Approach to Regulation of Nuclear Sites in England and Wales - 20058

The Environment Agency for England has developed a systematic evidence-based approach to pursue our strategic environmental objectives for the regulation of nuclear sites. We use an annual evidence review process to ensure effective and efficient targeting of limited resources to achieve those objectives. Over the last 8 years, we have been developing and refining this approach to ensure risk-based and value driven regulation. The approach comprises nuclear site and nuclear sector review processes known as Site Environment Review (SER) and Nuclear Environment Review (NER). This approach complements our regulation of nuclear site permit holders under the Environmental Permitting Regulations (EPR). We deliver our regulation of nuclear sites in England and Wales alongside the Office for Nuclear Regulation. The SER process involves the lead regulator for each nuclear site assessing the permit holder's environmental performance across 14 themes, set within the context of the site's main activities and associated waste disposals. Our themes include environmental leadership, resources and climate change, radioactive waste management, facility management and decommissioning, groundwater, and environmental radiological protection. We use evidence from site inspections and working within our subject matter groups to grade current and predicted future environmental performance. We are particularly interested in sustainability and the application of Best Available Techniques (BAT) to prevent the creation, and minimise the disposal, of radioactive wastes. We use risk analysis (strengths, weaknesses, threats and opportunities) to examine performance against our strategic environmental objectives, which are set out, in our 5-year Nuclear Delivery Plan (NDP). The output supports the targeting of our resources at each nuclear site. We consult the relevant permit holders on the SER priorities and use their feedback to refine our plans. We expect all permit holders to take account of our priorities when considering their own programmes of work, objectives and plans. The NER process brings together what we learn and achieve through regulation across the sector. It provides input to planning priorities, supported by qualitative and semi-quantitative evidence. It covers the 28 nuclear sites in England and Wales and spans the same 14 environmental themes. During the process we collate, compile and summarise evidence from the SERs and other sources such as inspection reports and evidence from our other nuclear work programmes. The output is the NER annual report. This provides a snapshot of the status of the nuclear sector and gives insights to enable us to regulate more efficiently and effectively. It also takes account of cross-cutting issues and risks such as changes in international standards, domestic policy, regulatory framework, domestic standards and guidance, learning from experience such as incidents, events and good practice, and innovation, research and development. It provides graphics that illustrate the grading of environmental performance for the nuclear sector across the fourteen environmental themes. This analysis allows benchmarking of nuclear site's environmental performance and the visualisation provides a convenient comparison of performance across themes, sites, and over time. We use this intelligence to inform our investment in training and development of our staff, and our cross-cutting engagement on strategic issues with government, the Nuclear Decommissioning Authority (NDA) and other corporate organisations. Adopting this approach can provide benefits with organisational reputation, stakeholder participation and ensuring value from the public investment. This paper describes the history of the SER/NER process, a selection of outputs from the process and ideas for improvement. The paper will be of interest to other regulators and organisations across the world that are interested in supporting continuous improvement. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Ohio River Basin Water Resources: Monitoring Flash Drought Potential and Quantifying the Hydrologic Impacts in the Ohio River Basin Utilizing NASA Earth Observations

Flash drought conditions emerge in a matter of weeks following persistent weather anomalies, such as high temperatures or large vapor pressure deficits, that drive increased evaporative demand. Vegetation response rapidly depletes soil moisture, threatening surface water supplies, triggering significant crop loss, and increasing wildfire risk. Drought indices sensitive to flash drought are currently not included in drought forecast models in the Ohio River Basin (ORB). The team assessed and compared drought indices, gauge-based data, and satellite measurements over the course of the September 2019 flash drought event in the Ohio River Basin to investigate environmental fingerprints throughout flash drought evolution. Potential leading flash drought indicators were compared to the Standardized Precipitation Index (SPI) to aid the National Weather Service (NWS) Ohio River Forecast Center and Kentucky Climate Center in producing early warning flash drought forecasts. These drought indices included Evaporative Demand Drought Index (EDDI), Standardized Precipitation Evapotranspiration Index (SPEI), and Landscape Evaporative Response Index (LERI) (derived from Terra Moderate Resolution Imaging Spectroradiometer (MODIS)). Drought index behavior inherently varies based on parameters incorporated -EDDI measures evaporative demand through potential evapotranspiration, and and demonstrates more variations due to sensitivity to seasonal changes in evaporative demand throughout the 2010-2019 study period. Conversely, LERI measures evaporative response through actual evapotranspiration, representing different environmental changes. Soil moisture response was evaluated using Soil Moisture Active Passive (SMAP) L-band radiometer data and Kentucky Mesonet gauge-based measurements. This analysis enables climatologists and weather forecasters to keep decision-makers and stakeholders better informed about drought risks to implement the appropriate actions for preparation of drought onset.

DEVELOP Project Summary↗

Constraints and Potentials of Future Irrigation Water Availability on Agricultural Production Under Climate Change

Freshwater availability is relevant to almost all socioeconomic and environmental impacts of climate and demographic change and their implications for sustainability. We compare ensembles of water supply and demand projections driven by ensemble output from five global climate models. Our results suggest reasons for concern. Direct climate impacts to maize, soybean, wheat, and rice involve losses of 400–2,600 Pcal (8–43% of present-day total). Freshwater limitations in some heavily irrigated regions could necessitate reversion of 20–60 Mha of cropland from irrigated to rainfed management, and a further loss of 600–2,900 Pcal. Freshwater abundance in other regions could help ameliorate these losses, but substantial investment in infrastructure would be required. We compare ensembles of water supply and demand projections from 10 global hydrological models and six global gridded crop models. These are produced as part of the Inter-Sectoral Impacts Model Intercomparison Project, with coordination from the Agricultural Model Intercomparison and Improvement Project, and driven by outputs of general circulation models run under representative concentration pathway 8.5 as part of the Fifth Coupled Model Intercomparison Project. Models project that direct climate impacts to maize, soybean, wheat, and rice involve losses of 400–1,400 Pcal (8–24% of present-day total) when CO2 fertilization effects are accounted for or 1,400–2,600 Pcal (24–43%) otherwise. Freshwater limitations in some irrigated regions (western United States; China; and West, South, and Central Asia) could necessitate the reversion of 20–60 Mha of cropland from irrigated to rainfed management by end-of-century, and a further loss of 600–2,900 Pcal of food production. In other regions (northern/eastern United States, parts of South America, much of Europe, and South East Asia) surplus water supply could in principle support a net increase in irrigation, although substantial investments in irrigation infrastructure would be required.

agriculture↗

Image Change Detection via Ensemble Learning

The concept of geographic change detection is relevant in many areas. Changes in geography can reveal much information about a particular location. For example, analysis of changes in geography can identify regions of population growth, change in land use, and potential environmental disturbance. A common way to perform change detection is to use a simple method such as differencing to detect regions of change. Though these techniques are simple, often the application of these techniques is very limited. Recently, use of machine learning methods such as neural networks for change detection has been explored with great success. In this work, we explore the use of ensemble learning methodologies for detecting changes in bitemporal synthetic aperture radar (SAR) images. Ensemble learning uses a collection of weak machine learning classifiers to create a stronger classifier which has higher accuracy than the individual classifiers in the ensemble. The strength of the ensemble lies in the fact that the individual classifiers in the ensemble create a mixture of experts in which the final classification made by the ensemble classifier is calculated from the outputs of the individual classifiers. Our methodology leverages this aspect of ensemble learning by training collections of weak decision tree based classifiers to identify regions of change in SAR images collected of a region in the Staten Island, New York area during Hurricane Sandy. Preliminary studies show that the ensemble method has approximately 11.5% higher change detection accuracy than an individual classifier.

Martin, Benjamin W↗