scholarly journals UAV and Machine Learning Based Refinement of a Satellite-Driven Vegetation Index for Precision Agriculture

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2530 ◽  
Author(s):  
Vittorio Mazzia ◽  
Lorenzo Comba ◽  
Aleem Khaliq ◽  
Marcello Chiaberge ◽  
Paolo Gay
Keyword(s):  
Satellite Imagery ◽  
Precision Agriculture ◽  
Vegetation Index ◽  
Management Practices ◽  
Normalized Difference Vegetation Index ◽  
High Efficiency ◽  
Cost Effective ◽  
Inaccurate Information ◽  
Agricultural Applications ◽  
Aerial Vehicle

Precision agriculture is considered to be a fundamental approach in pursuing a low-input, high-efficiency, and sustainable kind of agriculture when performing site-specific management practices. To achieve this objective, a reliable and updated description of the local status of crops is required. Remote sensing, and in particular satellite-based imagery, proved to be a valuable tool in crop mapping, monitoring, and diseases assessment. However, freely available satellite imagery with low or moderate resolutions showed some limits in specific agricultural applications, e.g., where crops are grown by rows. Indeed, in this framework, the satellite’s output could be biased by intra-row covering, giving inaccurate information about crop status. This paper presents a novel satellite imagery refinement framework, based on a deep learning technique which exploits information properly derived from high resolution images acquired by unmanned aerial vehicle (UAV) airborne multispectral sensors. To train the convolutional neural network, only a single UAV-driven dataset is required, making the proposed approach simple and cost-effective. A vineyard in Serralunga d’Alba (Northern Italy) was chosen as a case study for validation purposes. Refined satellite-driven normalized difference vegetation index (NDVI) maps, acquired in four different periods during the vine growing season, were shown to better describe crop status with respect to raw datasets by correlation analysis and ANOVA. In addition, using a K-means based classifier, 3-class vineyard vigor maps were profitably derived from the NDVI maps, which are a valuable tool for growers.

UAV application for precision agriculture

2019 ◽  
Vol 91 (2) ◽  
pp. 257-263 ◽  
Author(s):  
Rafal Perz ◽  
Kacper Wronowski
Keyword(s):  
Precision Agriculture ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Cost Effective ◽  
High Quality ◽  
Lower Altitude ◽  
Content Type ◽  
Agriculture Industry ◽  
Study Results ◽  
Forest Industries

Purpose The purpose of this study is to show the potentials of a cost-effective unmanned aerial vehicles (UAV) system for agriculture industry. The current population growth rate is so vast that farming industry must be highly efficient and optimized. As a response for high quality food demands, the new branch of the agriculture industry has been formed – the precision agriculture. It supports farming process with sensors, automation and innovative technologies. The UAV advantages over regular aviation are withering. Not only they can fly at lower altitude and are more precise but also offer same high quality and are much cheaper. Design/methodology/approach The main objective of this project was to implement an exemplary cost-effective UAV system with electronic camera stabilizer for gaining useful data for agriculture. The system was based on small, unmanned flying wing able to perform fully autonomous missions, a commercially available camera and an own-design camera stabilizer. The research plan was to integrate the platform and run numerous experimental flights over farms, fields and woods collecting aerial pictures. All the missions have been planned to serve for local farming and forest industries and cooperated with local business authorities. Findings In preliminary flight tests, the variety of geodetic, forest and agriculture data have been acquired, placed for post processing and applied for the farming processes. The results of the research were high quality orthophoto maps, 3D maps, digital surface models and images mosaics with normalized difference vegetation index. The end users were astonished with the high-quality results and claimed the high importance for their business. Originality/value The case study results proved that this kind of a small UAV system is exceptional to manage and optimize processes at innovative farms. So far only professional, high-cost UAV platforms or traditional airships have been applied for agriculture industry. This paper shows that even simple, commercially available equipment could be used for professional applications.

scholarly journals Detection of Spatial and Temporal Variability of Wheat Cultivars by High-Resolution Vegetation Indices

Agronomy ◽  
2019 ◽  
Vol 9 (5) ◽  
pp. 226 ◽  
Author(s):  
Stefano Marino ◽  
Arturo Alvino
Keyword(s):  
High Resolution ◽  
Precision Agriculture ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Vegetation Indices ◽  
Growth Stages ◽  
Spatial And Temporal Variability ◽  
Area Index ◽  
Aerial Vehicle ◽  
High Resolution Images

An on-farm research study was carried out on two small-plots cultivated with two cultivars of durum wheat (Odisseo and Ariosto). The paper presents a theoretical approach for investigating frequency vegetation indices (VIs) in different areas of the experimental plot for early detection of agronomic spatial variability. Four flights were carried out with an unmanned aerial vehicle (UAV) to calculate high-resolution normalized difference vegetation index (NDVI) and optimized soil-adjusted vegetation index (OSAVI) images. Ground agronomic data (biomass, leaf area index (LAI), spikes, plant height, and yield) have been linked to the vegetation indices (VIs) at different growth stages. Regression coefficients of all samplings data were highly significant for both the cultivars and VIs at anthesis and tillering stage. At harvest, the whole plot (W) data were analyzed and compared with two sub-areas characterized by high agronomic performance (H) yield 20% higher than the whole plot, and low performances (L), about 20% lower of yield related to the whole plot). The whole plot and two sub-areas were analyzed backward in time comparing the VIs frequency curves. At anthesis, more than 75% of the surface of H sub-areas showed a VIs value higher than the L sub-plot. The differences were evident also at the tillering and seedling stages, when the 75% (third percentile) of VIs H data was over the 50% (second percentile) of the W curve and over the 25% (first percentile) of L sub-plot. The use of high-resolution images for analyzing the frequency value of VIs in different areas can be a useful approach for the detection of agronomic constraints for precision agriculture purposes.

Beyond Cloud: A Fused Optic and SAR Based Solution to Monitor Crop Health

2021 ◽  
Author(s):  
Brianna Pagán ◽  
Adekunle Ajayi ◽  
Mamadou Krouma ◽  
Jyotsna Budideti ◽  
Omar Tafsi
Keyword(s):  
Machine Learning ◽  
Satellite Imagery ◽  
Cloud Cover ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Learning Approaches ◽  
Area Index ◽  
Spatial And Temporal Scales ◽  
Field Level ◽  
Crop Health

<p>The value of satellite imagery to monitor crop health in near-real time continues to exponentially grow as more missions are launched making data available at higher spatial and temporal scales. Yet cloud cover remains an issue for utilizing vegetation indexes (VIs) solely based on optic imagery, especially in certain regions and climates. Previous research has proven the ability to reconstruct VIs like the Normalized Difference Vegetation Index (NDVI) and Leaf Area Index (LAI) by leveraging synthetic aperture radar (SAR) datasets, which are not inhibited by cloud cover. Publicly available data from SAR missions like Sentinel-1 at relatively decent spatial resolutions present the opportunity for more affordable options for agriculture users to integrate satellite imagery in their day to day operations. Previous research has successfully reconstructed optic VIs (i.e. from Sentinel-2) with SAR data (i.e. from Sentinel-1) leveraging various machine learning approaches for a limited number of crop types. However, these efforts normally train on individual pixels rather than leveraging information at a field level. </p><p>Here we present Beyond Cloud, a product which is the first to leverage computer vision and machine learning approaches in order to provide fused optic and SAR based crop health information. Field level learning is especially well-suited for inherently noisy SAR datasets. Several use cases are presented over agriculture fields located throughout the United Kingdom, France and Belgium, where cloud cover limits optic based solutions to as little as 2-3 images per growing season. Preliminary efforts for additional features to the product including automated crop and soil type detection are also discussed. Beyond Cloud can be accessed via a simple API which makes integration of the results easy for existing dashboards and smart-ag tools. Overall, these efforts promote the accessibility of satellite imagery for real agriculture end users.</p><p> </p>

scholarly journals A Case Study about the Use of Precision Agriculture Technology Applied to a Zn Biofortification Workflow for Grapevine Vitis vinifera cv Moscatel

2021 ◽  
Vol 3 (1) ◽  
pp. 2
Author(s):  
Diana Daccak ◽  
Inês Carmo Luís ◽  
Ana Coelho Marques ◽  
Ana Rita F. Coelho ◽  
Cláudia Campos Pessoa ◽  
...  
Keyword(s):  
Vitis Vinifera ◽  
Precision Agriculture ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Foliar Application ◽  
Fold Increase ◽  
Production Cycle ◽  
Smart Farming ◽  
Reduced Surface

As the human population is growing worldwide, the food demand is sharply increasing. Following this assumption, strategies to enhance the food production are being explored, namely, smart farming, for monitoring crops during the production cycle. In this study, a vineyard of Vitis vinifera cv. Moscatel located in Palmela (N 38°35′47.113′′ O 8°40′46.651) was submitted to a Zn biofortification workflow, through foliar application of zinc oxide (ZnO) or zinc sulfate (ZnSO4) (at a concentration of 60% and 90%—900 g·ha−1 and 1350 g·ha−1, respectively). The field morphology and vigor of the vineyard was performed through Unmanned Aerial Vehicles (UAVs) images (assessed with altimetric measurement sensors), synchronized by GPS. Drainage capacity and slopes showed one-third of the field with reduced surface drainage and a maximum variation of 0.80 m between the extremes (almost flat), respectively. The NDVI (Normalized Difference Vegetation Index) values reflected a greater vigor in treated grapes with treatment SZn90 showing a higher value. These data were interpolated with mineral content, monitored with atomic absorption analysis (showing a 1.3-fold increase for the biofortification index). It was concluded that the used technologies furnishes specific target information in real time about the crops production.

scholarly journals New 30 m resolution Hong Kong climate, vegetation, and topography rasters indicate greater spatial variation than global grids within an urban mosaic

2019 ◽  
Vol 11 (3) ◽  
pp. 1083-1098 ◽  
Author(s):  
Brett Morgan ◽  
Benoit Guénard
Keyword(s):  
Hong Kong ◽  
Precision Agriculture ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
City Planning ◽  
Rapid Urbanization ◽  
Local Climate ◽  
Spatial Understanding ◽  
Environmental And Ecological Studies ◽  
Relevant Variables

Abstract. The recent proliferation of high-quality global gridded environmental datasets has spurred a renaissance of studies in many fields, including biogeography. However, these data, often 1 km at the finest scale available, are too coarse for applications such as precise designation of conservation priority areas and regional species distribution modeling, or purposes outside of biology such as city planning and precision agriculture. Further, these global datasets likely underestimate local climate variations because they do not incorporate locally relevant variables. Here we describe a comprehensive set of 30 m resolution rasters for Hong Kong, a small tropical territory with highly variable terrain where intense anthropogenic disturbance meets a robust protected area system. The data include topographic variables, a Normalized Difference Vegetation Index raster, and interpolated climate variables based on weather station observations. We present validation statistics that convey each climate variable's reliability and compare our results to a widely used global dataset, finding that our models consistently reflect greater climatic variation. To our knowledge, this is the first set of published environmental rasters specific to Hong Kong. We hope this diverse suite of geographic data will facilitate future environmental and ecological studies in this region of the world, where a spatial understanding of rapid urbanization, introduced species pressure, and conservation efforts is critical. The dataset (Morgan and Guénard, 2018) is accessible at https://doi.org/10.6084/m9.figshare.6791276.

scholarly journals Identification of Surface Water Storing Sites Using Topographic Wetness Index (TWI) and Normalized Difference Vegetation Index (NDVI)

2018 ◽  
Vol 8 ◽  
pp. 91-100
Author(s):  
Belete Berhanu ◽  
Ethiopia Bisrat
Keyword(s):  
Surface Water ◽  
Water Resource ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Cost Effective ◽  
Water Shortage ◽  
Sample Volume ◽  
Runoff Generation ◽  
Topographic Wetness Index ◽  
Wetness Index

Ethiopia is endowed with water and has a high runoff generation area compared to many countries, but the total stored water only goes up to approximately 36BCM. The problem of water shortage in Ethiopia emanates from the seasonality of rainfall and the lack of infrastructure for storage to capture excess runoff during flood seasons. Based on this premise, a method for a syndicate use of topography, land use and vegetation was applied to locate potential surface water storing sites. The steady-state Topographic Wetness Index (TWI) was used to represent the spatial distribution of water flow and water stagnating across the study area and the Normalized Difference Vegetation Index (NDVI) was used to detect surface water through multispectral analysis. With this approach, a number of water storing sites were identified in three categories: primary sources (water bodies based), secondary sources (Swampy/wetland based) and tertiary sources (the land based). A sample volume analysis for the 120354 water storing sites in category two, gives a 44.92BCM potential storing capacity with average depth of 4 m that improves the annual storage capacity of the country to 81BCM (8.6 % of annual renewable water sources). Finally, the research confirmed the TWI and NDVI based approach for water storing sites works without huge and complicated earth work; it is cost effective and has the potential of solving complex water resource challenges through spatial representation of water resource systems. Furthermore, the application of remote sensing captures temporal diversity and includes repetitive archives of data, enabling the monitoring of areas, even those that are inaccessible, at regular intervals.

Evaluating the Persistence of Post-Wildfire Ash: A Multi-Platform Spatiotemporal Analysis

Fire ◽  
2021 ◽  
Vol 4 (4) ◽  
pp. 68
Author(s):  
Sarah A. Lewis ◽  
Peter R. Robichaud ◽  
Andrew T. Hudak ◽  
Eva K. Strand ◽  
Jan U. H. Eitel ◽  
...  
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Field Measurements ◽  
Cost Effective ◽  
Spatiotemporal Analysis ◽  
Short Wave ◽  
Hydrologic Model ◽  
Landsat 8 ◽  
Data Volume ◽  
Sentinel 2

As wildland fires amplify in size in many regions in the western USA, land and water managers are increasingly concerned about the deleterious effects on drinking water supplies. Consequences of severe wildfires include disturbed soils and areas of thick ash cover, which raises the concern of the risk of water contamination via ash. The persistence of ash cover and depth were monitored for up to 90 days post-fire at nearly 100 plots distributed between two wildfires in Idaho and Washington, USA. Our goal was to determine the most ‘cost’ effective, operational method of mapping post-wildfire ash cover in terms of financial, data volume, time, and processing costs. Field measurements were coupled with multi-platform satellite and aerial imagery collected during the same time span. The image types spanned the spatial resolution of 30 m to sub-meter (Landsat-8, Sentinel-2, WorldView-2, and a drone), while the spectral resolution spanned visible through SWIR (short-wave infrared) bands, and they were all collected at various time scales. We that found several common vegetation and post-fire spectral indices were correlated with ash cover (r = 0.6–0.85); however, the blue normalized difference vegetation index (BNDVI) with monthly Sentinel-2 imagery was especially well-suited for monitoring the change in ash cover during its ephemeral period. A map of the ash cover can be used to estimate the ash load, which can then be used as an input into a hydrologic model predicting ash transport and fate, helping to ultimately improve our ability to predict impacts on downstream water resources.

scholarly journals Remote Sensing of Wildfire Using a Small Unmanned Aerial System: Post-Fire Mapping, Vegetation Recovery and Damage Analysis in Grand Bay, Mississippi/Alabama, USA

Drones ◽  
2019 ◽  
Vol 3 (2) ◽  
pp. 43 ◽  
Author(s):  
Sathishkumar Samiappan ◽  
Lee Hathcock ◽  
Gray Turnage ◽  
Cary McCraine ◽  
Jonathan Pitchford ◽  
...  
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Cost Effective ◽  
Recovery Process ◽  
Turnaround Time ◽  
Coastal Marsh ◽  
Vegetation Recovery ◽  
Burned Area ◽  
Surface Model ◽  
Unmanned Aerial System

Wildfires can be beneficial for native vegetation. However, wildfires can impact property values, human safety, and ecosystem function. Resource managers require safe, easy to use, timely, and cost-effective methods for quantifying wildfire damage and regeneration. In this work, we demonstrate an approach using an unmanned aerial system (UAS) equipped with a MicaSense RedEdge multispectral sensor to classify and estimate wildfire damage in a coastal marsh. We collected approximately 7.2 km2 of five-band multispectral imagery after a wildfire event in February 2016, which was used to create a photogrammetry-based digital surface model (DSM) and orthomosaic for object-based classification analysis. Airborne light detection and ranging data were used to validate the accuracy of the DSM. Four-band airborne imagery from pre- and post-fire were used to estimate pre-fire health, post-fire damage, and track the vegetation recovery process. Immediate and long-term post-fire classifications, area, and volume of burned regions were produced to track the revegetation progress. The UAS-based classification produced from normalized difference vegetation index and DSM was compared to the Landsat-based Burned Area Reflectance Classification. Experimental results show the potential of using UAS and the presented approach compared to satellite-based mapping in terms of classification accuracies, turnaround time, and spatial and temporal resolutions.

Sign in / Sign up

Export Citation Format

Share Document