UAV &amp; satellite synergies for optical remote sensing applications: A literature review

Alvarez-Vanhard, Emilien; Corpetti, Thomas; Houet, Thomas

doi:10.1016/j.srs.2021.100019

Cited by 157 publications

(98 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As highlighted above, UAVs are constantly gaining ground against satellites mainly because of their flexibility and ability to provide images with high resolution under any weather conditions. Satellites, on the other hand, can supply time-series over large areas [ 102 ]. Finally, animal welfare-related studies used mainly devices such as accelerometers for activity recognition, whereas those ones referring to livestock production utilized primary physical and growth characteristics of the animal.…”

Section: Discussion and Main Conclusionmentioning

confidence: 99%

Machine Learning in Agriculture: A Comprehensive Updated Review

Benos

Tagarakis

Dolias

et al. 2021

Sensors

390

146

View full text Add to dashboard Cite

The digital transformation of agriculture has evolved various aspects of management into artificial intelligent systems for the sake of making value from the ever-increasing data originated from numerous sources. A subset of artificial intelligence, namely machine learning, has a considerable potential to handle numerous challenges in the establishment of knowledge-based farming systems. The present study aims at shedding light on machine learning in agriculture by thoroughly reviewing the recent scholarly literature based on keywords’ combinations of “machine learning” along with “crop management”, “water management”, “soil management”, and “livestock management”, and in accordance with PRISMA guidelines. Only journal papers were considered eligible that were published within 2018–2020. The results indicated that this topic pertains to different disciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used, with those belonging to Artificial Neural Networks being more efficient. In addition, maize and wheat as well as cattle and sheep were the most investigated crops and animals, respectively. Finally, a variety of sensors, attached on satellites and unmanned ground and aerial vehicles, have been utilized as a means of getting reliable input data for the data analyses. It is anticipated that this study will constitute a beneficial guide to all stakeholders towards enhancing awareness of the potential advantages of using machine learning in agriculture and contributing to a more systematic research on this topic.

show abstract

Section: Discussion and Main Conclusionmentioning

confidence: 99%

Machine Learning in Agriculture: A Comprehensive Updated Review

Benos

Tagarakis

Dolias

et al. 2021

Sensors

390

146

View full text Add to dashboard Cite

show abstract

“…The increasing availability of quantitative field‐based vegetation data at the global scale (Bruelheide et al., 2019) may facilitate the estimation of the shade factor. The use of new remote sensing technologies including new satellites, drones and airborne LiDAR (Emilien et al., 2021; Ferraz et al., 2020; Valbuena et al., 2020) can also provide quantitative data to discriminate between closed and open ecosystems at large scales. Field information is also available to calibrate remote sensing data.…”

Section: Modelling Beyond Gleasonian Assumptionsmentioning

confidence: 99%

Alternative biome states challenge the modelling of species' niche shifts under climate change

Pausas

Bond

2021

Journal of Ecology

View full text Add to dashboard Cite

It is common to characterise the species niche using climate and global species distribution maps. This is then used to predict changes in distribution under a warming climate. This approach assumes that climate is a major driver of species distribution and that each species responds individually (sensu Gleason) to climate. However, in many world landscapes, for a given climate, strikingly different vegetation types co‐occur: forests and non‐forests. These two alternative biome states are maintained by different feedback processes and have radically different species with contrasting shade and disturbance tolerance traits. We propose that to improve predictions of species distribution changes under a novel climate, we need to consider the presence or absence of forest shade, as species are likely to respond individually only within their forest or non‐forest biome, and not across biomes. Synthesis. By considering shade as a biotic filter in niche modelling, we are not only improving our predictive capacity, but we are also reconciling the two views of communities: both the individualistic (within biome) and the organismal (across biomes) views of the community concept become relevant and complementary.

show abstract

“…For such dynamic coastal environments, new tasking capabilities of high spatial resolution satellite imagery of sub-daily temporal resolution 33 present a possibility for further research. In such satellite-based applications, UAV data may serve as a means to bridge the spatial and temporal gap between field and satellite image data 34 for observing dynamic features such as coastal water flows and exchanges.…”

Section: Discussionmentioning

confidence: 99%

Dye tracing and concentration mapping in coastal waters using unmanned aerial vehicles

Johansen

Dunne

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Coastal water flows facilitate important nutrient exchanges between mangroves, seagrasses and coral reefs. However, due to the complex nature of tidal interactions, their spatiotemporal development can be difficult to trace via traditional field instrumentations. Unmanned aerial vehicles (UAVs) serve as ideal platforms from which to capture such dynamic responses. Here, we provide a UAV-based approach for tracing coastal water flows using object-based detection of dye plume extent coupled with a regression approach for mapping dye concentration. From hovering UAV images and nine subsequent flight surveys covering the duration of an ebbing tide in the Red Sea, our results show that dye plume extent can be mapped with low omission and commission errors when assessed against manual delineations. Our results also demonstrated that the interaction term of two UAV-derived indices may be employed to accurately map dye concentration (coefficient of determination = 0.96, root mean square error = 7.78 ppb), providing insights into vertical and horizontal transportation and dilution of materials in the water column. We showcase the capabilities of high-frequency UAV-derived data and demonstrate how field-based dye concentration measurements can be integrated with UAV data for future studies of coastal water flow dynamics.

show abstract

UAV & satellite synergies for optical remote sensing applications: A literature review

Cited by 157 publications

References 74 publications

Machine Learning in Agriculture: A Comprehensive Updated Review

Machine Learning in Agriculture: A Comprehensive Updated Review

Alternative biome states challenge the modelling of species' niche shifts under climate change

Dye tracing and concentration mapping in coastal waters using unmanned aerial vehicles

Contact Info

Product

Resources

About