Machine learning and remote sensing techniques applied to estimate soil indicators – Review

Ecological Indicators, Journal Year: 2021, Volume and Issue: 135, P. 108517 - 108517

Published: Dec. 30, 2021

The demand for food based on intensive agriculture has decreased soil quality, posing great challenges such as increasing agricultural productivity and promoting environmental sustainability. Thus, researchers have focused developing models estimating quality artificial intelligence techniques the processing of multidimensional data from agro-industrial systems, which provide useful information farmers about management crop conditions. However, a model application these new technologies in medium low-scale systems not been identified. Therefore, review recent studies yield prediction estimation chemical, physical, biological indicators (SQI), incorporate different machine learning (ML) to process remote sensing (RS) is presented. advantages disadvantages are also analyzed for: SQI estimates at regional local scale, spectral bands used analysis plowed soils (bare soils) cultivation plots, selection minimun set (MDS), use unmanned aerial vehicle (UAV) satellite platforms, pre-processing, ML algorithms databases (agro-industrial systems). Finally, we present help estimate RS data, inputs unit come four class sets (RS, SQI, data). Crop uses production adjust practices therefore improve yield.

Language: Английский

---

Recent advances in the remote sensing of insects

Biological reviews/Biological reviews of the Cambridge Philosophical Society, Journal Year: 2021, Volume and Issue: 97(1), P. 343 - 360

Published: Oct. 5, 2021

ABSTRACT Remote sensing has revolutionised many aspects of ecological research, enabling spatiotemporal data to be collected in an efficient and highly automated manner. The last two decades have seen phenomenal growth capabilities for high‐resolution remote that increasingly offers opportunities study small, but ecologically important organisms, such as insects. Here we review current applications using within entomological highlighting the emerging now arise through advances spatial, temporal spectral resolution. can used map environmental variables, habitat, microclimate light pollution, capturing on topography, vegetation structure composition, luminosity at spatial scales appropriate Such also detect insects indirectly from influences they environment, feeding damage or nest structures, whilst directly detecting are available. Entomological radar detection ranging (LiDAR), example, transforming our understanding aerial insect abundance movement ecology, ultra‐high resolution drone imagery presents tantalising new direct observation. is rapidly developing into a powerful toolkit entomologists, envisage will soon become integral part science.

Language: Английский

---

Forest tree species distribution for Europe 2000–2020: mapping potential and realized distributions using spatiotemporal machine learning

PeerJ, Journal Year: 2022, Volume and Issue: 10, P. e13728 - e13728

Published: July 25, 2022

This article describes a data-driven framework based on spatiotemporal machine learning to produce distribution maps for 16 tree species ( Abies alba Mill., Castanea sativa Corylus avellana L., Fagus sylvatica Olea europaea Picea abies L. H. Karst., Pinus halepensis nigra J. F. Arnold, pinea sylvestris Prunus avium Quercus cerris ilex robur suber and Salix caprea L.) at high spatial resolution (30 m). Tree occurrence data total of three million points was used train different algorithms: random forest, gradient-boosted trees, generalized linear models, k-nearest neighbors, CART an artificial neural network. A stack 305 coarse covariates representing spectral reflectance, biophysical conditions biotic competition as predictors realized distributions, while potential modelled with environmental only. Logloss computing time were select the best algorithms tune ensemble model stacking logistic regressor meta-learner. An trained each species: probability uncertainty produced using window 4 years six per species, distributions only one map produced. Results cross validation show that consistently outperformed or performed good individual in both tasks, models achieving higher predictive performances (TSS = 0.898, R 2 logloss 0.857) than ones average 0.874, 0.839). Ensemble Q. achieved 0.968, 0.952) 0.959, 0.949) distribution, P. 0.731, 0.785, 0.585, 0.670, respectively, distribution) 0.658, 0.686, 0.623, 0.664) worst. Importance predictor variables differed across green band summer Normalized Difference Vegetation Index (NDVI) fall diffuse irradiation precipitation driest quarter (BIO17) being most frequent important distribution. On average, fine-resolution (250 m) +6.5%, +7.5%). The shows how combining continuous consistent Earth Observation series state art can be derive dynamic maps. predictions quantify temporal trends forest degradation composition change.

Language: Английский

---

Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors

Sensors, Journal Year: 2021, Volume and Issue: 21(1), P. 320 - 320

Published: Jan. 5, 2021

Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes vegetation cover can provide relevant information dryland conservation ecology. For this reason, improving understanding the effect resolution on results is improve monitoring. We explored analyzed accuracy Object-Based Image Analysis (OBIA) Mask Region-based Convolutional Neural Networks (Mask R-CNN) fusion both a ecosystem. As case study, we mapped Ziziphus lotus, dominant shrub habitat priority one driest areas Europe. Our show first time that from OBIA R-CNN increases shrubs up 25% compared separately. Hence, by fusing R-CNNs images, improved mapping would lead more precise sensitive biodiversity ecosystem services

Language: Английский

---

Evaluating fine-scale phenology from PlanetScope satellites with ground observations across temperate forests in eastern North America

Remote Sensing of Environment, Journal Year: 2022, Volume and Issue: 283, P. 113310 - 113310

Published: Oct. 20, 2022

Language: Английский

---

Characterisation of Banana Plant Growth Using High-Spatiotemporal-Resolution Multispectral UAV Imagery

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(3), P. 679 - 679

Published: Jan. 23, 2023

The determination of key phenological growth stages banana plantations, such as flower emergence and plant establishment, is difficult due to the asynchronous habit plants. Identifying events assists growers in determining maturity, harvest timing guides application time-specific crop inputs. Currently, monitoring requires repeated manual observations individual plants’ stages, which highly laborious, time-inefficient, handling integration large field-based data sets. ability accurately forecast yield also compounded by Satellite remote sensing has proved effective spatial temporal phenology many broadacre crops. However, for crops, very high resolution imagery required enable level monitoring. Unoccupied aerial vehicle (UAV)-based technologies provide a cost-effective solution, with potential derive information on health, yield, timely, consistent, quantifiable manner. Our research explores UAV-derived track changes plants from follower establishment harvest. Individual crowns were delineated using object-based image analysis, calculations canopy height area producing strong correlations against corresponding ground-based measures these parameters (R2 0.77 0.69 respectively). A profile reflectance morphology 15 selected derived UAV-captured multispectral over 21 UAV campaigns. was validated determinations stages. Derived minimum provided strongest harvest, whilst interpolated maxima normalised difference vegetation index (NDVI) best indicated emergence. For pre-harvest forecasting, Enhanced Vegetation Index 2 relationship = 0.77) captured near These findings demonstrate that UAV-based multitemporal can be used determine growing offer forecasts.

Language: Английский

---

Practical Guidelines for Performing UAV Mapping Flights with Snapshot Sensors

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(4), P. 606 - 606

Published: Feb. 10, 2025

Uncrewed aerial vehicles (UAVs) have transformed remote sensing, offering unparalleled flexibility and spatial resolution across diverse applications. Many of these applications rely on mapping flights using snapshot imaging sensors for creating 3D models the area or generating orthomosaics from RGB, multispectral, hyperspectral, thermal cameras. Based a literature review, this paper provides comprehensive guidelines best practices executing such flights. It addresses critical aspects flight preparation execution. Key considerations in covered include sensor selection, height GSD, speed, overlap settings, pattern, direction, viewing angle; execution on-site preparations (GCPs, camera calibration, reference targets) as well conditions (weather conditions, time flights) to take into account. In all steps, high-resolution high-quality data acquisition needs be balanced with feasibility constraints time, volume, post-flight processing time. For reflectance measurements, BRDF issues also influence correct setting. The formulated are based consensus. However, identifies knowledge gaps particularly angle general. aim advance harmonization UAV practices, promoting reproducibility enhanced quality

Language: Английский

---

CrowNet: a trail-camera canopy monitoring system

Agricultural and Forest Meteorology, Journal Year: 2025, Volume and Issue: 372, P. 110596 - 110596

Published: June 1, 2025

Language: Английский

---

Monitoring canopy-scale autumn leaf phenology at fine-scale using unmanned aerial vehicle (UAV) photography

Agricultural and Forest Meteorology, Journal Year: 2023, Volume and Issue: 332, P. 109372 - 109372

Published: Feb. 17, 2023

Language: Английский

---

Monitoring spring leaf phenology of individual trees in a temperate forest fragment with multi-scale satellite time series

Remote Sensing of Environment, Journal Year: 2023, Volume and Issue: 297, P. 113790 - 113790

Published: Sept. 1, 2023

Language: Английский

---