SEARCH · Engineering Papers

Results for “Demonstration Projects”

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.

SourceResearch connectionFrom yearThrough year

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

At least 541 records · Page 30

All sources NASA NTRS DOE OSTI

DOE OSTI2013

Retrofit of a Multifamily Mass Masonry Building in New England

Merrimack Valley Habitat for Humanity (MVHfH) has partnered with Building Science Corporation to provide high performance affordable housing for 10 families in the retrofit of an existing brick building (a former convent) into condominiums. The research performed for this project provides information regarding advanced retrofit packages for multi-family masonry buildings in Cold climates. In particular, this project demonstrates safe, durable, and cost-effective solutions that will potentially benefit millions of multi-family brick buildings throughout the East Coast and Midwest (Cold climates). The retrofit packages provide insight on the opportunities for and constraints on retrofitting multifamily buildings with ambitious energy performance goals but a limited budget. The condominium conversion project will contribute to several areas of research on enclosures, space conditioning, and water heating. Enclosure items include insulation of mass masonry building on the interior, airtightness of these types of retrofits, multi-unit building compartmentalization, window selection, and roof insulation strategies. Mechanical system items include combined hydronic and space heating systems with hydronic distribution in small (low load) units, and ventilation system retrofits for multifamily buildings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2014

HPC4Energy Final Report : GE Energy

Power System planning tools are being used today to simulate systems that are far larger and more complex than just a few years ago. Advances in renewable technologies and more pervasive control technology are driving planning engineers to analyze an increasing number of scenarios and system models with much more detailed network representations. Although the speed of individual CPU’s has increased roughly according to Moore’s Law, the requirements for advanced models, increased system sizes, and larger sensitivities have outstripped CPU performance. This computational dilemma has reached a critical point and the industry needs to develop the technology to accurately model the power system of the future. The hpc4energy incubator program provided a unique opportunity to leverage the HPC resources available to LLNL and the power systems domain expertise of GE Energy to enhance the GE Concorda PSLF software. Well over 500 users worldwide, including all of the major California electric utilities, rely on Concorda PSLF software for their power flow and dynamics. This pilot project demonstrated that the GE Concorda PSLF software can perform contingency analysis in a massively parallel environment to significantly reduce the time to results. An analysis with 4,127 contingencies that would take 24 days on a single core was reduced to 24 minutes when run on 4,217 cores. A secondary goal of this project was to develop and test modeling techniques that will expand the computational capability of PSLF to efficiently deal with systems sizes greater than 150,000 buses. Toward this goal the matrix reordering implementation time was sped up 9.5 times by optimizing the code and introducing threading.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2015

H- Ion Sources for High Intensity Proton Drivers

Existing RF Surface Plasma Sources (SPS) for accelerators have specific efficiencies for H + and H - ion generation around 3 to 5 mA/cm 2 per kW, where about 50 kW of RF power is typically needed for 50 mA beam current production. The Saddle Antenna (SA) SPS described here was developed to improve H- ion production efficiency, reliability and availability for pulsed operation as used in the ORNL Spallation Neutron Source . At low RF power, the efficiency of positive ion generation in the plasma has been improved to 200 mA/cm 2 per kW of RF power at 13.56 MHz. Initial cesiation of the SPS was performed by heating cesium chromate cartridges by discharge as was done in the very first versions of the SPS. A small oven to decompose cesium compounds and alloys was developed and tested. After cesiation, the current of negative ions to the collector was increased from 1 mA to 10 mA with RF power 1.5 kW in the plasma (6 mm diameter emission aperture) and up to 30 mA with 4 kW RF power in the plasma and 250 Gauss longitudinal magnetic field. The ratio of electron current to negative ion current was improved from 30 to 2. Stable generation of H- beam without intensity degradation was demonstrated in the aluminum nitride (AlN) discharge chamber for 32 days at high discharge power in an RF SPS with an external antenna. Some modifications were made to improve the cooling and cesiation stability. The extracted collector current can be increased significantly by optimizing the longitudinal magnetic field in the discharge chamber. While this project demonstrated the advantages of the pulsed version of the SA RF SPS as an upgrade to the ORNL Spallation Neutron Source, it led to a possibility for upgrades to CW machines like the many cyclotrons used for commercial applications. Four appendices contain important details of the work carried out under this grant.

43 PARTICLE ACCELERATORS↗

DOE OSTI2013

Retrofit of a MultiFamily Mass Masonry Building in New England

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2024

Stratus and Stratocumulus Cloud Microphysics and Drizzle Relationships With CCN Modality

High resolution extended-range cloud condensation nuclei (CCN) spectral comparisons with cloud microphysics and drizzle of the Physics of Stratocumulus Tops (POST) field experiment confirmed results in the Marine Stratus/Stratocumulus Experiment (MASE). Both of these stratus cloud projects demonstrated that bimodal CCN spectra typically caused by cloud processing were associated with clouds that exhibited higher concentrations of smaller droplets with narrower distributions and less drizzle than clouds associated with unimodal CCN spectra. Resulting brighter clouds and increased cloudiness could enhance both indirect aerosol effects (IAE). These stratus findings are opposite of analogous measurements in two cumulus cloud projects, which showed bimodal CCN associated with fewer larger droplets more broadly distributed and with more drizzle than clouds associated with unimodal CCN. Resulting reduced cumulus brightness and cloudiness could reduce both IAE. Physics of Stratocumulus Tops (POST) flights in air masses with higher CCN concentrations, N CCN , showed more extremes of the stratus characteristics. However, POST flights with lower N CCN showed opposite droplet characteristics similar to the cumulus clouds, yet still showed less drizzle in clouds associated with bimodal CCN, but not as much less as the flights with higher N CCN . Since all MASE clouds were in polluted air masses, while the two cumulus projects were in clean air masses we deduce from these four projects that both the dynamic stratus/cumulus differences (vertical wind) and N CCN are responsible for the microphysics and drizzle differences among these projects. This is because the clean POST characteristics are a hybrid between MASE/POST high N CCN and the two cumulus projects.

bimodality↗

DOE OSTI2025

EM-Enhanced HyPOR Loop for Fast Fusion Cycles

Vacuum pumps are the heart of a fusion energy facility – fusion power cannot be generated without them. Nevertheless, the vacuum technology needed to operate a viable fuel cycle for a compact fusion power plant does not exist. Commercial vacuum technology offers the best solution to this challenge, but a pump oil recycling and detritiation system is necessary. Conventional oil detritiation processes have only been developed to deal with legacy waste and are too slow and destructive to the oil. Further, post hoc detritiation strategies are intrinsically inefficient. Our approach is to rethink the challenge holistically by designing the pumping fluid and tritium extraction system in an integrated manner to achieve an innovative solution. By selecting an oil for the specific task of pumping tritium and then designing our catalytic system to selectively target the tritium-bearing functional groups, an effective detritiation system (hydrocarbon pump oil recycling, HyPOR, loop) for fusion power plants can be obtained. The project demonstrated a HyPOR loop process that can selectively remove heavier hydrogen isotopes from pump oil, reaching the target of 99.5 % removal, with an uptake of less than 0.01% of tritium throughput, while also purifying the oil of radiation-induced damage. The recycled oil retained its pumping characteristics over 7 recycles and gamma irradiation over 30 MGy. By meeting these targets, the project enable a reduction in pump operational costs from $\$$14.5M/year to $\$$103k/year (>140× reduction), reducing pump electric power consumption from 2.8 MW to 0.25 MW (>10× reduction), and reducing in-process tritium inventory from 2.03 kg to 0.48 kg (>4× reduction).

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2014

Development of Rhodobacter as a Versatile Microbial Platform for Fuels Production

The overall goal of the project was to genetically engineer the C30 triterpene hydrocarbons – squalene and botryococcene - in the heterologous host, Rhodobacter capsulatus. This host can grow autotrophically on CO 2 , H 2 and O 2 and there were indications of related species that could accept electrons directly from a cathode. Since water can be split into H 2 and O 2 by electrolysis, this provided alternative paths from renewable electrical energy to liquid fuels. The hydrocarbon target could not only provide a ‘drop in’ crude oil substitute, but its hydrophobicity would also provide ease of separation and thereby improve process economics over water miscible fuels such as ethanol. Combined with indications that Rhodobacter has a low baseline maintenance energy requirement, the research was focused on achieving economic feasibility through reduced process costs. This included an examination of bioreactor designs with low energy input for the delivery of the gases for consumption by the organism. The scope of the research therefore ranged from detailed process technoeconomic modeling, to metabolic engineering of the hydrocarbon biosynthetic pathways into Rhodobacter. The project demonstrated technical feasibility of producing triterpene hydrocarbons in Rhodobacter, and even some success in the acceptance of electrons by a consortium of bacteria from an electrode. However, the process economic models indicate that the rates of these biological processes are not yet sufficient to provide a fuel-producing process at typical costs of renewable energy generation such as solar photovoltaics. The project trained over 20 students in this highly interdisciplinary project context, with two of the students taking on faculty positions before the completion of the project.

10 SYNTHETIC FUELS↗

DOE OSTI2021

Hydrothermal Liquid Recovery of Rare Earth Elements and Critical Materials

This project demonstrated the technical viability of using tunable hydrothermal liquid (HTL) solutions to recover valuable minerals from a range of source materials. The effort focused upon rare earth elements (REE) and other minerals critical to the industrial security of the United States. This effort demonstrated, for the first time, that s, supercritical water (SCW) in particular, can: Extract critical and valuable minerals from a range of matrices ranging from rock ore to biomass; The process can be used to recover a wide range of minerals; This novel extraction chemistry can be cheap, simple, and nontoxic/”green”: The chemical extraction uses water, the cheapest industrial acid (sulfuric), and simple salts (i.e. sodium sulfate). However, other acids, salts, and additives could be used as appropriate. This Laboratory Directed Research and Development (LDRD) project identified that the process is complex with many interacting factors, but the benefits are significant if the complexities can be resolved. Challenges remain in the development of this technology and are described in this report. However, the results are positive, and commercial partners have already expressed interest. In summary, a novel, green, inexpensive mineral extraction process has been developed and demonstrated in a small batch reactor system. The effort provided information for an invention disclosure, proposal to DOE, and will support future business development efforts.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

Phase I Summary of Management Activities - Advanced Construction Technology Initiative Project

As the end of the year is approached, it is essential to review the National Reactor Innovation Center (NRIC) management activities undertaken during the Advanced Construction Technology Initiative (ACTI) project. The ACTI project was launched to support a transformation in nuclear energy construction, management, and deployment costs, enabling nuclear energy to make important contributions to the energy systems of the future. This transformation will increase the confidence of investors, energy system planners, policymakers, and ultimately consumers in the capability of nuclear energy to meet future needs; thus, it represents a critical element of advanced nuclear energy system demonstration. Development and/or demonstration project(s) will consider regulatory requirements for commercial nuclear implementation and will incorporate strategies to develop regulator experience and review of the technology. GE Hitachi (GEH), a leading player in the nuclear industry that offers a range of products and services including nuclear reactor design, fuel supply, and decommissioning solutions, submitted a proposal for the ACTI project. GEH was awarded the contract for the first phase of the project.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2015

Integrating commercially available remote systems to address current D and D challenges - 15399

Many current D and D challenges across the DOE complex require some form of remote handling expertise and equipment. For example, high visibility projects such as Building 324 D and D and the recovery of wastes from the Alpha-Caissons and the 618 10-11 caissons at Hanford all require the development and application of advanced remote systems. Additionally although alternate solutions and options are being sought, robotic/remote systems will likely be required for completion of D and D at Savannah River Site's Building 235-F, at the West Valley Demonstration Project and many other DOE facilities that are scheduled for D and D. Similar systems are also needed to support the UK cleanup program on projects such as the decommissioning of the Pile Fuel Cladding Silo. As a result, there are a significant number of R and D and Technology Development projects underway in order to address the growing need for remote systems in D and D. In addition to these significant R and D efforts, there are also numerous remote systems in use in multiple applications in both nuclear and non-nuclear industries and the use of remote systems at the Fukushima Daiichi plant has been extensive in the past 12-24 months. In many cases, the systems developed are customized for their given application but there are also multiple systems in use which could be applied to the worldwide D and D challenge either directly or with some minor adaptation. During FY14, the Office of D and D and Facility Engineering (EM13) funded a review/assessment of the current state-of-the-art of robotics and remote technologies in order to generate a baseline of what is available, what has been used where and for what applications and what has been successful and what hasn't. Where possible, the assessment was extended to identify remote systems that have been used in non-nuclear industries but which, with limited modification, may have application in the nuclear industry. The work also included a review of the most recent publicly available TBuRD (Technical Baseline and Underpinning R and D) activities being undertaken by the UK NDA and their Site Licensed Companies (SLCs) in the area of remote systems in order to compile a searchable database of both available, commercial-off-the-shelf (COTS) remote systems and developing technologies. Other suitably qualified organizations in the US and the UK (such as UK National Nuclear Laboratory, SRNL, PNNL ORNL, OC Robotics and others) were also engaged to identify other ongoing technology development efforts which may be of interest and benefit to the decommissioning community. In all, of the order of 500 remote systems were identified and cataloged in both hard copy and as a searchable database. These systems were categorized in terms of their main application e.g. manipulator, wheeled land-based platform, track land-based platform, water-based platform, air-based platform, end effectors, sensor, crawler etc to clearly demonstrate the depth and breadth of available systems in each category. In addition, single page summaries of each system were produced and used, in a workshop setting, to identify technologies which, when integrated with other currently-available technologies, could provide a workable system to address existing needs. An initial workshop was held with CH2 Washington Idaho (CWI) and DOE Idaho in August 2014 to explore how the available systems could be integrated to address current and future D and D needs at that site. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2023

Modeling Gray Zone Tactics Used Against Green Energy Supply Chains

This report documents a project demonstrating capabilities within Lawrence Livermore National Laboratory’s Cyber and Infrastructure Resilience program to place newly developed numeric simulations into the current, larger geopolitical context. The emergence of state-backed gray zone threats introduces an unprecedented challenge because they fall short of armed conflict and involve ambiguous tactics, requiring a fresh analytical approach to understanding their potential impact and countering them. In the context of our project, we analyze how China might use gray zone tactics to degrade the power of the United States, including our influence over global efforts to combat climate change.

25 ENERGY STORAGE↗

DOE OSTI2017

Electric Power Generation from Low to Intermediate Temperature Resourcces

The UND-CLR Binary Geothermal Power Plant was a collaborative effort of the U.S. Department of Energy (DOE), Continental Resources, Inc. (CRL), Slope Electric Cooperative (SEC), Access Energy, LLC (AE), Basin Electric Cooperative (BEC), Olson Construction, the North Dakota Industrial Commission Renewable Energy Council (NDIC-REC), the North Dakota Department of Commerce Centers of Excellence Program (NDDC-COE), and the University of North Dakota (UND). The primary objective of project was to demonstrate/test the technical and economic feasibility of generating electricity from non-conventional, low-temperature (90 ºC to 150 °C) geothermal resources using binary technology. CLR provided the access to 98 ºC water flowing at 51 l s-1 at the Davis Water Injection Plan in Bowman County, ND. Funding for the project was from DOE –GTO, NDIC-REC, NDD-COE, and BEC. Logistics, on-site construction, and power grid access were facilitated by Slope Electric Cooperative and Olson Construction. Access Energy supplied prototype organic Rankine Cycle engines for the project. The potential power output from this project is 250 kW at a cost of $3,400 per kW. A key factor in the economics of this project is a significant advance in binary power technology by Access Energy, LLC. Other commercially available ORC engines have efficiencies 8 to 10 percent and produce 50 to 250 kW per unit. The AE ORC units are designed to generate 125 kW with efficiencies up to 14 percent and they can be installed in arrays of tens of units to produce several MW of power where geothermal waters are available. This demonstration project is small but the potential for large-scale development in deeper, hotter formations is promising. The UND team’s analysis of the entire Williston Basin using data on porosity, formation thicknesses, and fluid temperatures reveals that 4.0 x 1019 Joules of energy is available and that 1.36 x 109 MWh of power could be produced using ORC binary power plants. Much of the infrastructure necessary to develop extensive geothermal power in the Williston Basin exists as abandoned oil and gas wells. Re-completing wells for water production could provide local power throughout the basin thus reducing power loss through transmission over long distances. Water production in normal oil and gas operations is relatively low by design, but it could be one to two orders of magnitude greater in wells completed and pumped for water production. A promising method for geothermal power production recognized in this project is drilling horizontal open-hole wells in the permeable carbonate aquifers. Horizontal drilling in the aquifers increases borehole exposure to the resource and consequently increases the capacity for fluid production by up to an order of magnitude.

15 GEOTHERMAL ENERGY↗

NASA NTRS2004

The Mars laser communication demonstration

This paper provides the status of the Mars Laser Communication Demonstration Project, a joint project between NASA's Goddard Space Flight Center (GSFC), the California Institute of Technology Jet Propulsion Laboratory (JPL), and the Massachusetts Institute of Tecnology Lincoln Laboratory (MIT/LL). It reviews the current ideas/designs for the flight and ground segments, the critical technologies required, adn the concept of operations. The laser communication (lasercom) flight terminal will be flown on the Mars Telecom Orbiter (MTO) to be launched by NASA in 2009, and will demonstrate a technology which has the potential of vastly improving NASA's ability to communicate throughout the solar system.

DePaula, Ramon↗

DOE OSTI2015

Enabling Exascale Hardware and Software Design through Scalable System Virtualization (Final Report)

The purpose of this project has been to extend the state of the art of systems software for high-end computing (HEC) platforms, and to use systems software to better enable the evaluation of potential future HEC platforms, for example exascale platforms. Such platforms, and their systems software, have the goal of providing scientific computation at new scales, thus enabling new research in the physical sciences and engineering. Over time, the innovations in systems software for such platforms also become applicable to more widely used computing clusters, data centers, and clouds. This was a five-institution project, centered on the Palacios virtual machine monitor (VMM) systems software, a project begun at Northwestern, and originally developed in a previous collaboration between Northwestern University and the University of New Mexico. In this project, Northwestern (including via our subcontract to the University of Pittsburgh) contributed to the continued development of Palacios, along with other team members. We took the leadership role in (1) continued extension of support for emerging Intel and AMD hardware, (2) integration and performance enhancement of overlay networking, (3) connectivity with architectural simulation, (4) binary translation, and (5) support for modern Non-Uniform Memory Access (NUMA) hosts and guests. We also took a supporting role in support for specialized hardware for I/O virtualization, profiling, configurability, and integration with configuration tools. The efforts we led (1-5) were largely successful and executed as expected, with code and papers resulting from them. The project demonstrated the feasibility of a virtualization layer for HEC computing, similar to such layers for cloud or datacenter computing. For effort (3), although a prototype connecting Palacios with the GEM5 architectural simulator was demonstrated, our conclusion was that such a platform was less useful for design space exploration than anticipated due to inherent complexity of the connection between the instruction set architecture level and the microarchitectural level. For effort (4), we found that a code injection approach proved to be more fruitful. The results of our efforts are publicly available in the open source Palacios codebase and published papers, all of which are available from the project web site, v3vee.org. Palacios is currently one of the two codebases (the other being Sandia’s Kitten lightweight kernel) that underlies the node operating system for the DOE Hobbes Project, one of two projects tasked with building a systems software prototype for the national exascale computing effort.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2017

The dual effect of tubulin manipulation on Populus wood formation and drought tolerance

The main objectives were to generate transgenic Populus with altered alpha- (TUA) and beta-tubulin (TUB) expression and/or post-translational modifications (PTMs) in a plant-wide, guard cell-specific or xylem-specific manner, and then to characterize the effects of the modifications on tree growth and wood properties. In short, strong effects on cell wall composition were noted in leaves where transgene expression was strong (Harding et al. 2017; Hu et al. in review). Subtle, but noteworthy effects were observed in wood (developing xylem) where transgene expression was weak (Swamy et al. 2015). Any effect of PTM manipulation was functionally recessive and/or confounded by tubulin overexpression. It was anticipated that PTM manipulation would affect tubulin half-life, and this is the question that was being addressed, but overall tubulin protein levels correlated with transgene expression levels. We also demonstrated that a dynamic C-terminal PTM known as the tyrosination/detyrosination cycle, so common in animal systems, and purportedly operational in plants, does not occur in wood-forming tissues of Populus (Hu et al. 2016). Contrary to the commonly hypothesized role of microtubules in directing microfibril deposition, cellulose content and microfibril angle were not changed in tubulin-overexpressing plants, nor were hemicellulose and lignin contents, in either wood or leaves. Instead, this project demonstrated that the extractability of pectin and xylan polysaccharides was sensitive to tubulin perturbations, with consequences in stomatal stress response and lignocellulosic biomass utilization. The work also revealed a complex interplay by multi-compartmental (cell wall and cytoskeleton) signaling that impinged upon the control of phenylpropanoid metabolic flux to modulate stomatal response to environmental stimuli.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2022

Predicting and Controlling Corrosion (Abbreviated Final Report)

Corrosion accumulates significant replacement costs in the transportation, utility, manufacturing, and infrastructure sectors. It also underpins several of LLNL’s core missions in stockpile stewardship, defense, and energy security. Whereas most corrosion and aging models are empirically parameterized to describe well-defined conditions late in the reaction, the factors that determine the early stages of corrosion—during which mitigation could be most impactful— are poorly understood. This project addressed the critical need for new approaches to predict the kinetics of corrosion initiation based on firm physical and chemical understanding. The activities encompassed degradation of relevant metals in both hydrogen-rich and environmental corrosion scenarios. The team integrated state-of-the-art multiscale simulation, in situ characterization, and data science within three technical thrusts: hydriding of Ti alloys; aqueous corrosion of Al and Ni-Cr alloys; and degradation of additively manufactured 316L stainless steel. In each case, novel capabilities were developed to identify and track the impacts of key atomistic, compositional, and microstructural features on the metal systems. For hydriding, protocols were developed to tightly integrate multiscale models, advanced multimodal characterization, and machine learning to determine how hydrogen interacts with native passivating surface oxides and nucleates new undesired phases, shedding new light on the critical role of grain boundaries, interfaces, and atomically disordered regions. For aqueous corrosion, the project demonstrated methods to predict dissolution rates of metal surfaces in corrosive solutions, to measure and understand microstructural and grain orientation effects on corrosion susceptibility, and to investigate competing growth and dissolution kinetics of surface oxides. For additively manufactured metals, analysis using state-of-the-art microscopy techniques revealed the role of specific heterogeneities invoked during laser processing, including cellular structure, dislocations, and precipitates, on corrosion susceptibility. In addition to new capabilities and understanding, the project provided an avenue for workforce development, as well as key partnerships with stakeholders in corrosion science.

08 HYDROGEN↗

NASA NTRS2014

Design Concepts for Cooled Ceramic Matrix Composite Turbine Vanes

This project demonstrated that higher temperature capabilities of ceramic matrix composites (CMCs) can be used to reduce emissions and improve fuel consumption in gas turbine engines. The work involved closely coupling aerothermal and structural analyses for the first-stage vane of a high-pressure turbine (HPT). These vanes are actively cooled, typically using film cooling. Ceramic materials have structural and thermal properties different from conventional metals used for the first-stage HPT vane. This project identified vane configurations that satisfy CMC structural strength and life constraints while maintaining vane aerodynamic efficiency and reducing vane cooling to improve engine performance and reduce emissions. The project examined modifications to vane internal configurations to achieve the desired objectives. Thermal and pressure stresses are equally important, and both were analyzed using an ANSYS® structural analysis. Three-dimensional fluid and heat transfer analyses were used to determine vane aerodynamic performance and heat load distributions.

Boyle, Robert↗

DOE OSTI2025

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↗