The advent of generative AI exemplified by large language models (LLMs) opens new ways to represent and compute geographic information and transcends the process of geographic knowledge production, driving geographic information systems (GIS) towards autonomous GIS. Leveraging LLMs as the decision core, autonomous GIS can independently generate and execute geoprocessing workflows to perform spatial analysis. In this vision paper, we further elaborate on the concept of autonomous GIS and present a conceptual framework that defines its five autonomous goals, five levels of autonomy, five core functions, and three operational scales. We demonstrate how autonomous GIS could perform geospatial data retrieval, spatial analysis, and map making with four proof-of-concept GIS agents. We conclude by identifying critical challenges and future research directions, including fine-tuning and self-growing decision-cores, autonomous modelling, and examining the societal and practical implications of autonomous GIS. By establishing the groundwork for a paradigm shift in GIScience, this paper envisions a future where GIS moves beyond traditional workflows to autonomously reason, derive, innovate, and advance geospatial solutions to pressing global challenges. Meanwhile, we emphasize that as we design and deploy increasingly intelligent geospatial systems, we carry a responsibility to ensure they are developed in socially responsible ways, serve the public good, and support the continued value of human geographic insight in an AI-augmented future.

Human movements in urban areas are essential to understand human–environment interactions. However, activities and associated movements are full of uncertainties due to the complexity of a city. In this paper, we propose a novel sensor-based approach for spatiotemporal event detection based on the Discrete Empirical Interpolation Method. Specifically, we first identify the key locations, defined as “sensors”, which have the strongest correlation with the whole dataset. We then simulate a regular uneventful scenario with the observation data points from those key locations. By comparing the simulated and observation scenarios, events are extracted both spatially and temporally. We apply this method in New York City with taxi trip record data. Results show that this method is effective in detecting when and where events occur.

We describe the control and interfacing of a fluorometer designed for aerial drone-based measurements of chlorophyll-a using an Arduino Nano 33 BLE Sense board. This 64 MHz controller board provided suitable resolution and speed for analog-to-digital (ADC) conversion, processed data, handled communications via the Robot Operating System (ROS) and included a variety of built-in sensors that were used to monitor the fluorometer for vibration, acoustic noise, water leaks and overheating. The fluorometer was integrated into a small Uncrewed Aircraft System (sUAS) for automated water sampling through a Raspberry Pi master computer using the ROS. The average power consumption was 1.1 W. A signal standard deviation of 334 µV was achieved for the fluorescence blank measurement, mainly determined by the input noise equivalent power of the transimpedance amplifier. An ADC precision of 130 µV for 10 Hz chopped measurements was achieved for signals in the input range 0-600 mV.

This study investigates the use of small unoccupied aerial systems (sUAS) as a new remote sensing tool to identify and track the spatial distribution of wrack on coastal tidal marsh systems. We used sUAS to map the wrack movement in a Spartina alterniflora-dominated salt marsh monthly for one year including before and after Hurricane Isaias that brought strong winds, rain, and storm surge to the area of interest in August 2020. Flight parameters for each data collection mission were held constant including collection only during low tide. Wrack was visually identified and digitized in a GIS using every mission orthomosaic created from the mission images. The digitized polygons were visualized using a raster data model and a combination of all of the digitized wrack polygons. Results indicate that wrack mats deposited before and as a result of a hurricane event remained for approximately three months. Furthermore, 55% of all wrack detritus was closer than 10 m to river or stream water bodies, 64% were within 15 m, and 71% were within 20 m, indicating the spatial dependence of wrack location in a marsh system on water and water movement. However, following the passing of Isaias, the percentage of wrack closer than 10 m to a river or creek decreased to a low of 44%, which was not seen again during the year-long study. This study highlights the on-demand image collection of a sUAS for providing new insights into how quickly wrack distribution and vegetation can change over a short time.

Uncrewed Aircraft Systems (UAS) are increasingly used in time-consuming and effort-heavy scientific exploration applications. One such application is the inspection of the physical, chemical, and biological properties of water in aquatic ecosystems. This paper presents a novel autonomous UAS capable of sensing water properties and collecting up to three 250 mL water samples from multiple sampling locations. The system features a customized UAS with an in-house built fluorescence sensor and pumping mechanism. The system does in situ fluorescence measurements to map the gradient of fluorescent content across the body of water and determine the best sampling spot for targeted sampling. To ensure safe near-water operation, multiple sensor fusion with an Extended Kalman Filter has been implemented for accurate altitude estimation within 1.5 m from the water surface. To validate the performance of the system, we present experimental results from deployment in two different water ecosystems, namely the Congaree River, SC and Lake Wateree, SC.

We recently described a lightweight, low-power, waterproof filter fluorometer using a 180° backscatter geometry for chlorophyll-a (chl-a) detection. Before it was constructed it was modeled to ensure it would have satisfactory performance. This manuscript repeats the modeling process that allows the calibration slope and detection limit for a fluorescent analyte in water to be estimated from system component performance and conventional spectrofluorometry alone. These values are validated by comparison to the experimental result of calibration from the completed instrument. Our model yields a calibration slope of 8.22 mV-L/µg for dissolved chl-a, consistent with the experimentally measured slope of 8.21 mV-L/µg. The detection limit modeled from this slope and an estimate of the baseline noise of the instrument was 0.15 µg/L chl-a, while the measured detection limit using real blank samples was 0.18 µg/L, in 0.1 s differential measurements.

Mapping landscape change at fine scales (e.g. <1.0 m resolution) using airborne LiDAR data from manned aircraft is a significant challenge. This challenge is magnified in disaster response contexts. A combination of collection and processing factors contributes to horizontal and vertical errors (and resulting uncertainty) in each pre- and post-LiDAR derived digital elevation model (DEM). Subsequently, the errors in the change surface from the two (or more) DEMs are an accumulation of the errors in the individual DEMs. Thus, reliable mapping erosion/deposition changes at sub-meter precision in change detection studies using LiDAR data is largely the domain of terrestrial LiDAR or sUAS with LiDAR scanners rather than manned aircraft. Unfortunately, terrestrial and sUAS LiDAR scanners are not well suited for mapping large areas and sUAS collections are subject to additional airspace constraints compared to manned aircraft. In this study, we probed one of the significant issues in airborne LiDAR change projects - vertical height errors from sequential flight lines. A simplified solution for determining flight line vertical biases in areas of low topographic relief with natural cover types was developed and tested for normalizing point clouds. The approach was tested in a fine-scale erosion/deposition study from an extreme rainfall event that eroded and deposited sand at depths of about 1.0 m. Airborne LiDAR had been collected prior to the rainfall event, and another airborne LiDAR collection was made 1 month after the event. Eleven field campaigns to collect reference data and visit anomalies in the change surface were conducted in a 15-month period after the event, beginning 25 February 2016 and ending 8 May 2017. The validation results indicate accuracies for the pre-event and post-event LiDAR derived DEMs were 7.8 cm and 13.0 cm RMSE, respectively. After modeling vertical errors and corrections applied to the post-event point clouds, the RMSE for the post-event DEM was 8.3 cm. In the depositional use case, 27 locations were sampled with auger boreholes/sand pits and compared with LiDAR-based change. The LiDAR-based change detection analysis resulted in predicted sand depth accuracies of 94% with a mean error of 4.7 cm.

We describe a waterproof, lightweight (1.3 kg), low-power (∼1.1 W average power) fluorometer operating on 5 V direct current deployed on a small uncrewed aircraft system (sUAS) to measure chlorophyll and used for triggering environmental water sampling by the sUAS. The fluorometer uses a 450 nm laser modulated at 10 Hz for excitation and a standard photodiode and transimpedance amplifier for the detection of fluorescence. Additional detectors are available for measuring laser intensity and light scattering. Control of the fluorometer and communication between the fluorometer and the Raspberry Pi 4B computer controlling the sampler were provided by an Arduino microcontroller using the robot operating system (ROS). Calibrations were based on standards of dissolved chlorophyll extracted from Chlorella powder (a widely available dietary supplement). The detection limit for chlorophyll from these calibrations was found to be 0.2 μg per liter of water for a single 0.1 s differential measurement. The detection limit decreases with the square root of the integration time as expected. Detection limits increase by a factor of two to three when mounted in the sUAS due to electrical noise; sUAS acoustic noise and vibration do not appear to contribute significantly.

Street view images are now widely used in web map services, providing on-site photos of street scenes for users to explore without physically being in the field. These photos record detailed visual information of the street environment with geospatial controls; therefore, they can be used for metric mapping purposes. In this study, we present a method to convert street view images to measurable land cover maps using their associated depthmap data. The proposed method can autonomously extract and measure land cover objects over large areas covered by a mosaic of street view images. In the case study, we demonstrated the use of land cover maps derived from Google Street View images to extract sidewalk features and to measure sidewalk clear widths for wheelchair users. Sidewalk feature slopes were also extracted from the metadata of street view images. Using the Washington D.C., U.S. as the study area, our method extracted a sidewalk network of 2561 km in length with the precision of 0.8662 and recall of 0.8525. The width mean error of extracted sidewalks wide between 1 and 2 m is 0.24 m, and the slope mean error is 0.638. In Washington D.C., most sidewalks meet the minimum width requirement (0.9 m), but 20% of them have slopes that exceed the maximum allowance (1:20 or about 2.9 degrees). These results demonstrate the converted land cover maps from street view images can be used for metric mapping purposes. The extracted sidewalk network can serve as a valuable inventory for urban planners to promote equitable walkability for mobility disabled users. And if widely available, mobility-impaired users could consult them prior to planning a route.

Coastal wetlands contribute greatly to our coasts economically and ecologically. The utility of coastal wetland vegetation, along with the multitude of dynamic forces they encounter, suggests the need of regular monitoring for sustainable management. While traditional in situ survey methods and remote sensing from space and manned platforms have provided means to monitor and study the coastal zone thus far, the recent developments of small unmanned aerial systems (sUAS) fill a small void between traditional in situ survey methods and the high spatial resolution of manned aircraft imagery. As an on-demand personal remote sensing device, an sUAS can be deployed over coastal regions at a low cost and with very fine spatial resolution (i.e. 1–10 cm) imagery and corresponding spatial accuracy. Though an sUAS provides many benefits, recent literature documents several shortcomings and limitations to using them for coastal wetland vegetation research, including changing tides, lighting conditions and legal restrictions on flying. This study reviewed all coastal wetland vegetation-related studies that included an sUAS as a mapping tool to document the current state of the field. Current practices, successes, and limitations are described, and future directions for the field are discussed. Coastal managers and researchers alike will be able use this comprehensive review to determine how to best approach future studies of diverse coastal vegetation.

Water sensing and sampling is a complex application that can benefit from the use of aerial drones. In the monitoring of an aquatic environment, inspection of its physical, chemical, and biological states are equally important. In most cases, only the physical and chemical properties are investigated due to lack of portable sensor packages capable of in situ measurements of biological indicators. Additionally, biological sample collection for ex situ analysis poses certain challenges which requires specialized sample collection methods. For acquiring a good sample, remote sensing needs to work hand in hand with the sampling mechanism to capture the correct analyte of interest. This work presents the design and development of an aerial drone equipped with a custom-made sensor package and sampling mechanism, for sensing and non-destructive sampling of dissolved organic matter in aquatic environments. The developed system is experimentally validated in an outdoor setting and is shown to be capable for in situ measurements of fluorescent content of water bodies and sensor-triggered sample collection.

ABSTRACT An introduction in the use of small unmanned aerial systems for mapping is becoming a desirable course for undergraduate students. The controllability of drone aircraft and quality cameras, even in less expensive aerial models, offers opportunities for students to learn and collect their own imagery for a variety of applications. This opportunity can be taught with an active learning approach. The challenge for instructors is to cover the three fundamentals in the remote sensing workflow – planning, collection, and image processing – while minimizing logistical issues associated with actual flight operation. The logistical issues (e.g. policy, legal, safety, weather) for an outdoor aerial drone learning experience are quite daunting, particularly for urban campuses with local/state restrictions on the use of drone aircraft. In this article, we separate the fundamental learning concepts in the remote sensing workflow from the flight operation and provide a learning environment for unlimited experiments. Using a synthetic indoor scaled landscape, students are given the opportunity for repeat experiments in a tightly controlled environment, saving the focus on actual flight operation for later times in the semester. The advantages of the indoor landscape are many, and also minimize the logistical issues for actual flight operation.

Soil degradation is one of the main environmental issues within the international agendas on sustainability and climate adaptation. Among degradation processes, soil sealing represents the major threat, as ecosystem services dramatically decrease or are even nullified. The increasing use of big open data from satellites combined with AI algorithms are making geodata mining and mapping techniques essential to quantify soil sealing. Different keywords are adopted to define the phenomenon. However, at present, review articles presenting the state-of-the-art on mapping soil sealing by including the most common definitions are currently not available. Hence, we analyzed: (a) impervious surface, (b) soil sealing, (c) land take, (d) soil consumption, (e) land consumption. We provide a systematic review of remote sensing platforms and methodologies to map and to classify soil sealing, by highlighting: (a) definitions; (b) relationships among study areas, scales, platforms, resolutions, and classification methodologies; (c) emerging trends and policy implications. We performed a systematic search on Scopus (from 2000 to 2020), identifying 1277 papers; 392 focused on mapping soil sealing. ‘Impervious surface’ is the dominant definition. The phenomenon is more studied by the USA, China and Italy and, ‘soil sealing’ is recently more adopted in EU. Most studies focuses on mapping soil sealing at urban scale. We found Landsat are the most adopted platforms; they are frequently used for multi-temporal analyses. Eleven methodologies were identified: automatic classifications are the most adopted, dominated by pixel/sub-pixel-based approaches; other methods include Band Ratios, Supervised, OBIA, ANN. The majority of mapping analyses are performed on 30 m resolution in areas of 1000–10 000 km2. Landsat images are less used for smaller areas. In conclusion, as study area size increases, a decrease in image resolution with the use of more completely automatic classification methodologies is recorded. However, most studies focuses on comparing classification techniques rather than supporting policy making for sustainable urban planning. Thus, we encourage to fill the gap by developing approaches that applicable to international policies.

Mission planning for small uncrewed aerial systems (sUAS) as a platform for remote sensors goes beyond the traditional issues of selecting a sensor, flying altitude/speed, spatial resolution, and the date/time of operation. Unlike purchasing or contracting imagery collections from traditional satellite or manned airborne systems, the sUAS operator must carefully select launching, landing, and flight paths that meet both the needs of the remote sensing collection and the regulatory requirements of federal, state, and local regulations. Mission planning for aerial drones must consider temporal and geographic changes in the environment, such as local weather conditions or changing tidal height. One key aspect of aerial drone missions is the visibility of the aircraft and communication with the aircraft. In this research, a visibility model for low-altitude aerial drone operations was designed using a GIS-based framework supported by high spatial resolution LiDAR data. In the example study, the geographic positions of the visibility of an aerial drone used for water sampling at low altitudes (e.g., 2 m above ground level) were modeled at different levels of tidal height. Using geospatial data for a test-case environment at the Winyah Bay estuarine environment in South Carolina, we demonstrate the utility, challenges, and solutions for determining the visibility of a very low-altitude aerial drone used in water sampling.

Mapping the topographic surface and monitoring the change in such topographic surfaces has largely been a remote sensing-based solution for the last eighty years. The last few years has seen the dramatic rise in the use of small unmanned aerial systems (sUAS) for mapping both the topographic surface (in largely un-vegetated areas) and particularly, the overlying surface layer. How accurate are the sUAS derived elevation surfaces? How accurate are the change surfaces from a comparison of multi-date surfaces? How confident can the user be in the changes detected? Probing the expected accuracy for a topographic surface derived from low altitude sUAS imagery is a tad more problematic than many other types of remotely sensed imaging sensors. The precision and spatial resolution of the sUAS imagery, and subsequent digital elevation models (DEMs) is similar to the precision and spatial resolution of the very reference data sources used for accessing accuracy. In this research an approach was used to evaluate the performance of sUAS for creating digital elevation models on coastal sand dunes that did not change during ten repeat aerial collections at 40 m above ground level. A simple error budget model was used to empirically derive the intrinsic accuracy of the sUAS-derived topographic surface. The overall accuracy of the ten DEMs derived from independent aerial missions was 0.033 m root mean squared error (RMSE). The results indicate a confidence threshold of similar to 0.030 m can be typically used to separate 95% of the 'false' topographic changes mapped from two digital elevation models in this collection/processing context. By modeling and removing the reference data error (i.e. survey grade global navigation satellite systems (GNSS)-derived validation points) the average accuracy of the ten DEMs was 0.022 m (RMSE). (C) 2020 Elsevier B.V. All rights reserved.

Defined as “personal remote sensing”, small unmanned aircraft systems (sUAS) have been increasingly utilized for landscape mapping. This study tests a sUAS procedure of 3D tree surveying of a closed-canopy woodland on an earthen dam. Three DJI drones—Mavic Pro, Phantom 4 Pro, and M100/RedEdge-M assembly—were used to collect imagery in six missions in 2019–2020. A canopy height model was built from the sUAS-extracted point cloud and LiDAR bare earth surface. Treetops were delineated in a variable-sized local maxima filter, and tree crowns were outlined via inverted watershed segmentation. The outputs include a tree inventory that contains 238 to 284 trees (location, tree height, crown polygon), varying among missions. The comparative analysis revealed that the M100/RedEdge-M at a higher flight altitude achieved the best performance in tree height measurement (RMSE = 1 m). However, despite lower accuracy, the Phantom 4 Pro is recommended as an optimal drone for operational tree surveying because of its low cost and easy deployment. This study reveals that sUAS have good potential for operational deployment to assess tree overgrowth toward dam remediation solutions. With 3D imaging, sUAS remote sensing can be counted as a reliable, consumer-oriented tool for monitoring our ever-changing environment.

Coastal wetland mapping is often difficult because of the heterogeneous vegetation compositions and associated tidal effects. In this study, we employed the U-Net and developed an adaptive deep learning approach to map statewide salt marshes in estuarine emergent wetlands of South Carolina (SC), USA, from 20 Sentinel-2A&B images. Considering the spatial heterogeneity of the coastal environment, two NOAA National Estuarine Research Reserves (NERRs) in SC were examined, the North Inlet-Winyah Bay (NIWB) NERR for model training and the ACE Basin NERR for testing. A high-resolution land cover map in the NIWB was downloaded for the training process. Ground reference points recorded by the NERR, as well as Google Earth were utilized during the accuracy assessment. The highest overall accuracy (90%) was achieved when all scenes with 10 Sentinel bands and the Normalized Difference Vegetation Index (NDVI) were included. The time used to train the model was 5 h, while then the statewide classification was performed in 20 min. Low marsh and high marsh distributions were successfully delineated. Compared to the national marsh maps from the NOAA Coastal Change Analysis Program (C-CAP), this study refined the land cover details concerning low marsh and high marsh distributions on the SC coast. Owing to the computational power of the U-Net, the seasonality and tide influence on marsh classification were mitigated by using multi-temporal images. With images available, the deep learning approach developed in this study could be easily adopted in other coastal areas.

ABSTRACT Small unmanned aerial systems, or sUAS, remote sensing has much potential for monitoring vegetation cover and other phenomena due to its innate ability to capture very high spatial resolution imagery at low altitudes, for small areas, and with rapid planning. Remote sensing methodologies used in monitoring change from orbital and manned aerial remote sensing have been extensively researched and implemented. However, these same historic change detection methodologies have not been thoroughly tested with the new, very high spatial resolution imagery captured by sUAS, particularly the modest sUAS proliferating in the resource management agencies around the world. This study seeks to examine and understand the variability involved in using sUAS for change detection of vegetation cover by designing a confidence model, calibrating the model, and demonstrating the use of the model. Our research design involves a novel approach using multiple collections in a 1.6-hour period over a controlled environment where the land cover did not change. A confidence model was developed and calibrated in the controlled environment. A demonstration of the developed confidence model from the control environment was used for a hurricane impacted area. Coastal dune vegetation cover, essential for dune strength and growth, was monitored before and after Hurricane Irma impacted Harbor Island in coastal South Carolina. The results indicate that even though no actual change occurred during the controlled experiment, an average of 5.6% of the pixels indicated a false change of land cover. These false land cover discrepancies are caused from slight shadow movements, georegistration accuracies, multiple look angles and variable spectral response from a mosaic (i.e. 120 images) of imagery. It was also determined that much change in vegetation cover occurred as a result of inundation from Hurricane Irma, and confidences were high in assessing the change.

Accessibility is a topic of interest to multiple disciplines for a long time. In the last decade, the increasing availability of data may have exceeded the development of accessibility modeling approaches, resulting in a modeling gap. In part, this modeling gap may have resulted from the differences needed for single versus multimodal opportunities for access to services. With a focus on large volumes of transportation data, a new measurement approach, called Urban Accessibility Relative Index (UARI), was developed for the integration of multi-mode transportation big data, including taxi, bus, and subway, to quantify, visualize and understand the spatiotemporal patterns of accessibility in urban areas. Using New York City (NYC) as the case study, this paper applies the UARI to the NYC data at a 500-m spatial resolution and an hourly temporal resolution. These high spatiotemporal resolution UARI maps enable us to measure, visualize, and compare the variability of transportation service accessibility in NYC across space and time. Results demonstrate that subways have a higher impact on public transit accessibility than bus services. Also, the UARI is greatly affected by diurnal variability of public transit service.