Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “spatiotemporal”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Generation of Land Surface Reflectance with Combined Geo-KOMPSAT-2A AMI and Himawari 8 AHI Observations

The latest generation of geostationary satellites has opened a new era of Earth observations with unprecedented spatiotemporal resolution and spectral range. Together with GOES 16/17 ABI, FY4-A AGRI, and Himawari-8 AHI, a new Korean geostationary satellite (Geo-KOMPSAT-2A AMI) has operationally collected a full-disk image in 16 channels every ten minutes since July 2019, allowing diurnal land surface monitoring over a large proportion of Asia and all of Oceania. Retrieving accurate surface reflectance (SR) over land from GK-2A/AMI is a challenging but high priority objective. One of the challenges is the absence of a spectral band in the 2.2 m SWIR range from AMI, which is required by many atmospheric correction algorithms to retrieve atmospheric aerosol properties. To remedy this issue, we adopt a strategy that combines concurrent GK-2A/AMI and Himawari 8/AHI observations in order to derive AMI SR. We have adapted the NASA Multi-Angle Implementation of Atmospheric Correction (MAIAC) algorithm to process the data stream from Himawari 8/AHI. The advantages of the MAIAC algorithm is its capability to exploit the high temporal frequency and varying illumination geometry of the geostationary data for advanced cloud/snow detection, aerosol retrieval, and characterization of surface bidirectional reflectance properties. Leveraging the similarities of spectral bands and the sun-target-sensor geometry between AMI and AHI, we are able to create denser time series of observations and enhanced BRDF samples over most of the spatial coverage of AMI (and AHI). The combined stereo-type observations not only help derive SR for AMI but also enhance retrievals of the corresponding AHI surface products. We evaluate the resulting AMI SR using ground (AERONET) observations and corresponding MODIS products. Further, we discuss potential challenges in utilizing the geostationary satellite data for land surface monitoring.

geostationary satellite↗
NASA NTRS2020

Radiometric approach for the detection of picophytoplankton assemblages across oceanic fronts

Cell abundances of Prochlorococcus, Synechococcus, and autotrophic picoeukaryotes were estimated in surface waters using principal component analysis (PCA) of hyperspectral and multispectral remote-sensing reflectance data. This involved the development of models that employed multilinear correlations between cell abundances across the Atlantic Ocean and a combination of PCA scores and sea surface temperatures. The models retrieve high Prochlorococcus abundances in the Equatorial Convergence Zone and show their numerical dominance in oceanic gyres, with decreases in Prochlorococcus abundances towards temperate waters where Synechococcus flourishes, and an emergence of picoeukaryotes in temperate waters. Fine-scale in-situ sampling across ocean fronts provided a large dynamic range of measurements for the training dataset, which resulted in the successful detection of fine-scale Synechococcus patches. Satellite implementation of the models showed good performance (R(exp 2) > 0.50) when validated against in-situ data from six Atlantic Meridional Transect cruises. The improved relative performance of the hyperspectral models highlights the importance of future high spectral resolution satellite instruments, such as the NASA PACE mission’s Ocean Color Instrument, to extend our spatiotemporal knowledge about ecologically relevant phytoplankton assemblages.

Priscila Kienteca Lange↗
NASA NTRS2020

How Long Is Too Long? Variogram Analysis of AERONET Data to Aid Aerosol Validation and Intercomparison Studies

Geophysical data sets derived from satellite sensors, ground/airborne instrumentation, and computational models are often compared against each other. A common example is the validation of satellite aerosol optical depth (AOD) retrievals against measurements from Aerosol Robotic Network (AERONET) Sun photometers. Spatiotemporal mismatch between data set sampling means that uncaptured variation in the underlying geophysical field introduces apparent disagreement into such comparisons, known as representation or collocation matchup uncertainty. This study uses variogram analysis of AERONET data to estimate temporal mismatch uncertainties and decorrelation time scales for the global AERONET record. As well as total AOD, the fine‐ and coarse‐mode AODs, Ångström Exponent (AE), and fine‐mode fraction (FMF) of AOD are analyzed. Globally, a time difference of 30 min typically induces from 0.011–0.035 variation in AOD. For total, fine, and coarse AODs the typical time to decorrelation is around 2–10 days. For AE and FMF it is 3–33 days; that is, aerosol systems often persist significantly longer than individual events in them. Biomass burning regions tend to show the largest and fastest subdaily AOD variability and also longest times to decorrelation. Some sites show significant season‐to‐season variations in behavior. These results can be used to inform site‐specific time collocation thresholds for aerosol validation analyses and account for temporal variation when estimating data set uncertainty. They also have implications for comparisons between different satellite products or models, data aggregation, and time series analyses. Results are provided on a site‐by‐site basis to facilitate use by other researchers.

satellite↗
NASA NTRS2020

Surface melting over the Greenland ice sheet from enhanced resolution passive microwave brightness temperatures (1979–2019)

Surface melting is a major component of the Greenland ice sheet (GrIS) surface mass balance, affecting sea level rise through direct runoff and the modulation on ice dynamics and hydrological processes, supraglacially, englacially and subglacially. Passive microwave (PMW) brightness temperature observations are of paramount importance in studying the spatial and temporal evolution of surface melting in view of their long temporal coverage (1979–to date) and high temporal resolution (daily). However, a major limitation of PMW datasets has been the relatively coarse spatial resolution, being historically of the order of tens of kilometres. Here, we use a newly released passive microwave dataset (37 GHz, horizontal polarization) made available through the NASA MeASUREs program to study the spatiotemporal evolution of surface melting over the GrIS at an enhanced spatial resolution of 3.125 Km. We assess the outputs of different detection algorithms through data collected by Automatic Weather Stations (AWS) and the outputs of the MAR regional climate model. We found that surface melting is well captured using a dynamic algorithm based on the outputs of MEMLS model, capable to detect sporadic and persistent melting. Our results indicate that, during the reference period 1979–2019 (1988–2019), surface melting over the GrIS increased in terms of both duration, up to ~4.5 (2.9) days per decade, and extension, up to 6.9 % (3.6 %) of the GrIS surface extent per decade, according to the MEMLS algorithm. Furthermore, the melting season has started up to ~4 (2.5) days earlier and ended ~7 (3.9) days later per decade. We also explored the information content of the enhanced resolution dataset with respect to the one at 25 km and MAR outputs through a semi-variogram approach. We found that the enhanced product is more sensitive to local scale processes, hence confirming the potential interest of this new enhanced product for studying surface melting over Greenland at a higher spatial resolution than the historical products and monitor its impact on sea level rise. This offers the opportunity to improve our understanding of the processes driving melting, to validate modelled melt extent at high resolution and potentially to assimilate this data in climate models.

Surface melting↗
NASA NTRSDate not supplied

Unveiling Urban Pollution Patterns from a Bird’s-Eye View

Low-earth orbiting satellites have been observing the global distribution of nitrogen dioxide (NO2) since the 1990s and these observations have been used to identify pollution source regions, temporal trends, and links to health effects and community disparities. However, historically, space-based NO2 observations have been coarse in spatial and temporal resolution resulting in challenges in data interpretation and product validation; therefore, NASA developed airborne capabilities and measurements strategies to observe ultraviolet-visible (UV-VIS) trace gases at high temporal and spatial resolutions to unveiling never before seen spatiotemporal patterns over major urban hubs during recent air quality field studies. In this talk, Dr. Judd will share the story of these field studies with datasets collected from NASA’s airborne spectrometers, GeoTASO and GCAS, and how they integrate in with other space- and ground-based instrumentation to illustrate the conceptual model of air quality episodes in coastal urban environments, contribute to satellite validation and regional chemical transport model evaluation. These imagers have the capability to observe UV-VIS absorbing species, typically NO2 and HCHO, at spatial resolutions as fine as 250 m when observing from the upper-troposphere. Flight strategies allowed for the collection of repeated raster samples over urban areas multiple times per flight day in cities like Chicago, Los Angeles, and New York City, capturing never before seen pictures of the diurnal evolution of emissions, chemistry, and meteorology associated with NO2 heterogeneity. These airborne efforts help local air quality management better understand their air quality challenges as well as benefit the larger air quality community in preparation for geostationary air quality observations and the development of the global air quality observing system.

Laura Judd↗
NASA NTRSDate not supplied

ImageLabler: Labeling and Managing Image Data for Machine Learning in the Earth Sciences

While machine learning techniques for image classification have been around for a long time, storing and managing the vast number of images required as training data is still a problem for scientists. This is especially true for the field of Earth science, where only recently have experts begun using machine learning techniques for image-based phenomena classification. Image Labeler, a fast and scalable cloud-based tagging platform for Earth science images, seeks to improve upon existing methods of managing images and associated metadata, such as maintaining categorized folders of images on a local machine, a process that can be cumbersome and difficult to scale. The platform facilitates rapid development of image-based Earth science phenomena training datasets by allowing scientists to upload their existing imagery as well as extract new samples from open satellite imagery services made available through NASA’s Global Imagery Browse Service (GIBS). Image Labeler also supports GeoTIFF data, with capabilities such as displaying GeoTIFFs on an interactive map, drawing shapefiles over them, and tagging them with additional metadata. This allows scientists to perform spatiotemporal subsetting with geographic information and develop training data more quickly. Built using modern web technologies, Image Labeler includes additional capabilities such as team collaboration for large-scale image tagging projects. Users can download their data in a machine-learning-ready format, allowing scientists to spend time on experimentation rather than on the collection of training data. In this presentation, we demonstrate how Image Labeler seeks to become a one-stop image data management solution for machine learning applications in Earth science.

Ashish Acharya↗
NASA NTRSDate not supplied

Phenomena Portal: Large- Scale Visual Exploration of Atmospheric Phenomena

The Earth science community is experiencing a high influx of remote sensing data due to recent advancements in sensor technology. This enables the community to extend their research on a larger scale than ever before. Unfortunately, traditional data processing techniques do not scale well to these new, high volume data sources. State-of-the-art machine learning (ML) pipelines have been proven to overcome these burdens in various other fields but are underexploited within the physical sciences community. Moreover, ML is reliant on labeled data, which is currently sparsely available, owing to the fact that ML adoption is still in the early stages within the Earth and atmospheric science communities. To address these issues, we developed the Phenomena Portal, a visual exploration tool that uses ML to detect various atmospheric phenomena on a global scale. This allows the Earth and atmospheric science communities to view trends of occurrences of phenomena, identify potential relationships between them, and analyze spatiotemporal patterns over time. These detections can also serve as initial labeled data for ML research pertaining to the respective phenomena. The tool also incorporates feedback from subject matter experts to further improve the model detection accuracy, thereby facilitating human-in-the-loop. This presentation will provide an overview of the ML model development and cloud deployment. We also discuss the capabilities of the user interface for displaying the detections.

Muthukumaran Ramasubramanian↗
NASA NTRS2019

Disentangling the Drivers of the Summertime Ozone‐Temperature Relationship Over the United States

Summertime surface-level ozone (O3 ) is known to vary with temperature, but the relative roles of different processes responsible for causing the O3 -temperature relationship are not well quantified. In this study we use simulations of NASA's Global Modeling Initiative (GMI) chemical transport model (CTM) to isolate and assess the relative impact of atmospheric transport, chemistry, and emissions on O3 variability, events, and its correlation with temperature. Using observations from CASTNet in the contiguous United States, we show that the GMI CTM reproduces the spatiotemporal variability of O3 and the O3 -temperature relationship during the summer. We primarily focus on the total change in O3 due to a change in temperature (d O3 /d T). In regions with strong positive correlations between temperature and O3 such as the Northeast, Great Lakes, and Great Plains, temperature's association with transport primarily drives d O3 /d T with smaller contributions from temperature-dependent chemistry and anthropogenic emissions. There are regions, however, with near-zero correlation between temperature and O3 , and our findings suggest that transport is still an important driver of O3 variability in these regions, albeit not correlated with temperature. Transport is not directly dependent on temperature but rather is linked through an indirect association, and it is therefore important to understand the exact mechanisms that link transport to O3 and how these mechanisms will change in a warming world.

ozone, temperature, CTM↗
NASA NTRSDate not supplied

Application of the Global Precipitation Forecast dataset for Global Landslide Forecasting System

Landslides are extremely damaging, pervasive and cause fatalities and economic impacts. Extreme rainfall events, coupled with inopportune surface conditions, are the primary triggers of landslides around the world. Forecasting landslide events represent an area of open research. A global Landslide Hazard Assessment for Situational Awareness (LHASA) model has been created that provides near real-time dynamic landslide characterization using Integrated Multi-Satellite Retrievals for Global Precipitation Mission (IMERG). However, it does not provide information on prediction of landslides into future. This study considers how global precipitation forecast data compares to satellite rainfall at different spatiotemporal scales and outlines the potential for its use in landslide hazard prediction/forecasting system. NASA Goddard Earth Observing System (GEOS)-Forecast model assimilates new observations every 6 hours, at 00, 06, 12, and 18 UTC. The GEOS-Forecast model is initialized at 00 UTC and is evaluated with IMERG Early, using Multi-Radar Multi-Sensor gauge corrected (MRMS-GC) precipitation product as a reference over contiguous United States (CONUS). Categorical and continuous statistics along with probability density functions and cumulative distribution functions are considered to assess the performance of the precipitation products, with a focus on landslide hotspots. Seasonality appears to influence the performance of both the GEOS-Forecast and IMERG Early product. Moreover, the global comparison between the GEOS-Forecast and IMERG Early is carried out in terms of percentile difference, correlation, and bias maps. For extreme rainfall events in regions such as Mekong, Colombia, and Tajikistan, GEOS-Forecast appears to resolve high rainfall relative to IMERG Early more frequently. Validation over landslide points reveal that for 24hr rainfall accumulations > 100mm, GEOS-Forecast and IMERG coincide. GEOS-Forecast and IMERG Early precipitation matches more closely for tropical cyclones than other types of storms. Overall, the performance varies with respect to location, rainfall intensities, and type of precipitation events.

Sana Khan↗
NASA NTRS2021

Plumelets: Dynamic Filamentary Structures in Solar Coronal Plumes

Solar coronal plumes long seemed to possess a simple geometry supporting spatially coherent, stable outflow without significant fine structure. Recent high-resolution observations have challenged this picture by revealing numerous transient, small-scale, collimated out-flows (“jetlets”) at the base of plumes. The dynamic filamentary structure of solar plumes above these outflows, and its relationship with the overall plume structure, have remained largely unexplored. We analyzed the statistics of continuously observed fine structure in-side a single representative bright plume within a mid-latitude coronal hole during 2016 July2-3. By applying advanced edge-enhancement and spatiotemporal analysis techniques to ex-tended series of high-resolution images from the Solar Dynamics Observatory’s Atmospheric Imaging Assembly, we determined that the plume was composed of numerous time-evolving filamentary substructures, referred to as “plumelets” in this paper, that accounted for most of the plume emission. The number of simultaneously identifiable plumelets was positively correlated with plume brightness, peaked in the fully formed plume, and remained saturated thereafter. The plumelets had transverse widths of 10 Mm and intermittently supported upwardly propagating periodic disturbances with phase speeds of 190-260 km s−1and longitudinal wavelengths of 55-65 Mm. The characteristic frequency (3.5 mHz) is commensurate with that of solar p-modes. Oscillations in neighboring plumelets are uncorrelated, indicating that the waves could be driven by p-mode flows at spatial scales smaller than the plumelet separation. Multiple independent sources of outflow within a single coronal plume should impart significant fine structure to the solar wind that may be detectable by Parker Solar Probe and Solar Orbiter.

V M Uritsky↗
NASA NTRS2020

Particulate backscattering in the global ocean: A comparison of independent assessements

How well do we know the particulate backscattering coefficient (bbp) in the global ocean? Satellite lidar bbp has never been validated globally and few studies have compared lidar bbp to bbp derived from reflectances (via ocean color) or in-situ observations. Here we validate lidar bbp with autonomous biogeochemical Argo floats using a decorrelation analysis to identify relevant spatiotemporal matchup scales inspired by geographical variability in the Rossby radius of deformation. We compare lidar, float, and ocean color bbp at the same locations and times to assess performance. Lidar bbp outperforms ocean color, with a median percent error of 18% compared to 24% in the best case and a relative bias of -11% compared to -21%, respectively. Phytoplankton carbon calculated from ocean color and lidar exhibits basin-scale differences that can reach ± 50%.

ocean color↗
NASA NTRS2020

Time-Varying Ice Sheet Mask: Implications on Ice-Sheet Mass Balance and Crustal Uplift

Mass-balance estimates of the polar ice sheets presently rely on static ice masks to identify the area under investigation. However, the vintage of available ice masks can differ by more than a decade and the resolution of the imagery used to delineate ice extent can differ by an order of magnitude, despite evidence of ongoing ice-sheet retreat. We show that using a fine resolution, time-varying ice mask significantly improves mass-balance estimates of the northwestern sector of the Greenland Ice Sheet and affects interpretation of local crustal uplift. Accounting for ice margin retreat using a time-varying ice mask between 2003–2015 results in 1.0–6.8% less ice-sheet mass loss relative to assuming one of several existing static ice masks. This indicates that mass-balance estimates that use a static ice mask will progressively overestimate mass loss where the ice sheet is predominantly retreating, meaning a negative bias on mass-balance. This trend is anticipated to be amplified in a future warming scenario unless updated ice masks are incorporated. For altimetry-derived mass-balance estimates, this ice-mask induced bias approaches the magnitude of the ice-sheet-wide uncertainty presently associated with spatiotemporal variability in modeled firn compaction. Further, at five GNET stations, the ice-mask-induced bias is equivalent to 5–15% of the modeled uplift due to elastic deformation. Given present and projected negative trends in Greenland Ice Sheet mass-balance and areal extent, we conclude that studies of its mass-balance should begin incorporating dynamic, periodically updated, fine-resolution ice masks. This methodological refinement will reduce bias in estimates of both ice-sheet mass-balance and crustal uplift.

Kristian K. Kjeldsen↗
NASA NTRS2021

The 2019-2020 Australian drought and bushfires altered the partitioning of hydrological fluxes

Though coarse in spatial resolution, the nearly all weather measurements from passive microwave sensors can help in improving the spatiotemporal coverage of optical and thermal infrared sensors for monitoring vegetation changes on the land surface. This study demonstrates the use of vegetation optical depth retrievals from the Soil Moisture Active Passive mission for capturing the vegetation alterations from the recent 2019-2020 Australian bushfires and drought. The impact of vegetation disturbance s on terrestrial water budget is examined by assimilating the vegetation optical depth retrievals into a dynamic phenology model. The results demonstrate that assimilating vegetation optical depth observations lead to improved simulation of evapotranspiration, runoff, and soil moisture states. The study also demonstrates that the vegetation changes from the 2019-2020 Australian drought and fires led to significant modifications in the partitioning of evaporative and runoff fluxes, resulting in increased bare soil evaporation, reduced transpiration, and higher runoff.

data assimilation↗
NASA NTRS2018

Probabilistic Guidance of a Swarm Deployed from the Back Shell of the Mars Spacecraft

This paper presents a probabilistic guidance algorithm for a swarm of assets deployed from the back shell of the Mars spacecraft. Such a swarm could provide valuable science data, with large spatiotemporal variation, from the Martian surface. Our probabilistic swarm guidance algorithm maximizes the coverage area of the swarm while uniformly distributing the assets on the Martian surface and guaranteeing strong connectivity of the swarm’s communication network topology. Numerical simulations demonstrate the effectiveness and versatility of our probabilistic swarm guidance algorithm.

Hadaegh, Fred↗
NASA NTRS2021

Assessing Disaggregated SMAP Soil Moisture Products in the United States

A soil moisture (SM) disaggregation algorithm based on thermal inertia (TI) theory was implemented to downscale the Soil Moisture Active Passive (SMAP) Enhanced product(SPL2SMPE) from 9 km to 1 km over the continental United States. The algorithm applies land surface temperature and normalized difference vegetation index from Moderate Resolution Imaging Spectroradiometer (MODIS) at higher spatial resolution to estimate relative soil wetness within a coarse SMAP grid -this MODIS-derived relative wetness is then used to produce the downscaled SMAP SM. Results from the algorithm were evaluated in terms of their spatiotemporal coverage and accuracy using in situ measurements from SMAP Core Validation Sites (CVS), the US Department of Agriculture Soil Climate Analysis Network (USDA-SCAN), and the National Oceanic and Atmospheric Administration Climate Reference Network(NOAA-CRN). Results were also compared with the baselineSPL2SMPE and the SMAP/Sentinel-1 (SPL2SMAPS) 1kmproduct. Overall, the unbiased root mean square error (ubRMSE)of the disaggregated SM at the CVS using the TI approach is approximately 0.04 m3=m3, which is the SMAP mission requirement for the baseline products. The TI approach out performs the SMAP/Sentinel SL2SMAPS 1km product by approximately0.02 m3=m3. Over the agriculture/crop areas from SCAN and CRN sparse network stations, the TI approach exhibits better ubRMSE compared to SPL2SMPE andSPL2SMAPS byabout0.01 and 0.02 m3=m3, indicating its advantage in these areas. However, a drawback of this approach is that there are data gaps due to cloud cover as optical sensors cannot have a clear view of the land surface.

Soil moisture↗
NASA NTRSDate not supplied

Impact of a Regional Drought on Land and Atmospheric Carbon over the North America

The spatiotemporal extent of a regional drought’s impact on land-atmosphere carbon and their mechanistic linkages are still poorly understood. Allowing carbon-water-energy feedback in an ensemble of coupled land-atmosphere simulations, this study quantifies induced changes in meteorology and carbon caused by an idealized 3-month meteorological drought over to the lower Mississippi River Valley (~500,000 km2). The imposed drought leads to a 23% Gross Primary Production (GPP) reduction in the drought area and the GPP reductions in some remote areas that are adjacent to the imposed drought through the changes in remote meteorology, particularly by the induced precipitation. The effect of the meteorological anomalies on GPP is greater, by at least an order of magnitude, than that of the atmospheric CO2 anomalies. While the magnitude of induced CO2 anomalies near the land surface can be as large as 3.57ppm, the column-averaged CO2 increases up to 0.78ppm and thus is below the precision limit (~1ppm) of current greenhouse gas (GHG) observing satellites. Spatially, the CO2 anomalies cover an area up to three times of that of the imposed drought, which suggests that the atmospheric transport needs to be considered in the interpretation of carbon anomalies in the atmosphere.

Eunjee Lee↗
NASA NTRS2020

Comparison of Vertical Surface Deformation Estimates Derived From Space-Based Gravimetry, Ground-Based GPS, and Model-Based Hydrologic Loading Over Snow-Dominated Watersheds in the United States

Spatiotemporal variability in Earth's terrestrial water storage (TWS) causes changes in surface deformation. The potential for using ground-based Global Positioning System (GPS) vertical displacement observations for estimating TWS is explored through a comparison of vertical displacements derived from space-based gravimetric retrievals, ground-based GPS, and model-based hydrologic estimates. The study presented here focuses on two snow-dominated basins in the Western United States for the years 2003–2016. Seasonal variations are observed in the vertical displacements derived from all three data sets, and the variation is coherent with the changes in hydrologic loading. Good consistency is observed between any two of the three data sets with gravimetric retrievals and hydrologic model estimates providing the highest level of agreement (i.e., all examined stations with correlation coefficient R > 0.70). Vertical displacements derived from gravimetric retrievals and ground-based GPS yielded R > 0.70 for more than 89% of the stations. In addition, it is found that both GPS-derived and space-based, gravimetry-derived vertical displacements clearly reflected the impact of climate variation (i.e., heavy precipitation during 2010–2011 winter followed by prolonged drought). Vertical displacements derived from the hydrologic model highlighted the relatively large precipitation convergence phase during late 2010 to early 2011 at some stations but not the prolonged drought that followed. The results indicate that ground-based GPS observations of vertical displacement have the capability to capture variations in TWS changes, which can be systematically merged in conjunction with Gravity Recovery and Climate Experiment (GRACE) into a land surface model to improve TWS estimates in a follow-up study.

Gaohong Yin↗
NASA NTRS2020

Remote monitoring of agricultural systems using NDVI time series and machine learning methods: a tool for an adaptive agricultural policy

This study aims to provide accurate information about changes in agricultural systems (AS) using phenological metrics derived from the NDVI time series. Use of such information could help land managers optimize land use choices and monitor the status of agricultural lands, under a variety of environmental and socioeconomic conditions. For this purpose, the Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI data were used to derive phenological metrics over the Oum Er-Rbia basin (central Morocco). Random forest (RF), support vector machine (SVM), and K-nearest neighbor (KNN) classifiers were explored and compared on their ability to classify AS classes over the study area. Four main AS classes have been considered: (1) irrigated annual crop (IAC), (2) irrigated perennial crop (IPC), (3) rainfed area (RA), and (4) fallow (FA). By comparing the accuracy of the three classifiers, the RF method showed the best performance with an overall accuracy of 0.97 and kappa coefficient of 0.96.The RF method was then chosen to examine time variations in AS over a 16-year period (2000–2016). The AS main variations were detected and evaluated for the four AS classes. These variations have been found to be linked well with other indicators of local agricultural land management, as well as the historical agricultural drought changes over the study area. Overall, the results present a tool for decision makers to improve agricultural management and provide a different perspective in understanding the spatiotemporal dynamics of agricultural systems.

Youssef Lebrini↗