On a Data-Driven Approach for Detecting Disturbance in the Brazilian Savannas Using Time Series of Vegetation Indices

Remote sensing of disturbance in the savannas from Brazil is challenging, especially due to confounding effects of the vegetation phenology and natural soil exposure on the detection of clearing and fire events. In this study, we investigated the detection of disturbance over this global hotspot of biodiversity using seven vegetation indices (VIs) calculated from the Landsat time series (2017–2019) and the Continuous Change Detection and Classification (CCDC) algorithm. The selected VIs represented distinct biophysical characteristics of the savannas. We evaluated the effects of disturbance on these VIs and assessed the accuracy of CCDC-detection in 2019, considering individual VIs, ensemble VIs, and the type of disturbance (savanna clearing and fire). Finally, we analyzed the possible existence of seasonal patterns of disturbance in a study area located at the new agricultural frontier of the Cerrado biome. The results showed that the overall accuracy of CCDC detection of total disturbance ranged from 51.2% for the Green-Red Normalized Difference (GRND) to 65.9% for the Normalized Burn Ratio (NBR2). It increased to 71.2% for ensemble VIs, whose multivariate approach reduced the omission errors in the analysis when compared to the use of single VIs. For detecting events of savanna clearing and fire, the most important VIs used near-infrared and shortwave infrared reflectance bands on their formulations (NBR2, NBR, and Moisture Stress Index—MSI). The CCDC accuracy was generally higher for detecting clearing than for mapping burned areas. In contrast, the recorded date of disturbance occurrence was less precise for detecting clearing than for recording events caused by fire, especially due to the existence of some gradual processes of vegetation degradation until complete clearing. Our findings showed also the existence of a seasonal pattern of disturbance occurrence. Savanna clearing predominated in the transition from the rainy to the dry season (April to July) to open new areas for agriculture. It preceded most events of fire disturbance between August and October that occurred near the consolidated areas of agriculture and extended into the native vegetation areas. Results reinforce the importance of data-driven approaches for generating early warning alerts of disturbance in the Cerrado to be further checked in the field.

Download Full-text

Seasonal dynamics of lingonberry and blueberry spectra

Silva Fennica ◽

10.14214/sf.10150 ◽

2019 ◽

Vol 53 (2) ◽

Author(s):

Petri Forsström ◽

Jouni Peltoniemi ◽

Miina Rautiainen

Keyword(s):

Vegetation Index ◽

Near Infrared ◽

Normalized Difference Vegetation Index ◽

Reference Data ◽

Leaf Growth ◽

Vegetation Indices ◽

Growing Season ◽

Moisture Stress ◽

Stress Index ◽

Infrared Spectral

Accurate mapping of the spatial distribution of understory species from spectral images requires ground reference data which represent the prevailing phenological stage at the time of image acquisition. We measured the spectral bidirectional reflectance factors (BRFs, 350â2500 nm) at varying view angles for lingonberry ( L.) and blueberry ( L.) throughout the growing season of 2017 using Finnish Geospatial Research Instituteâs FIGIFIGO field goniometer. Additionally, we measured spectra of leaves and berries of both species, and flowers of lingonberry. Both lingonberry and blueberry showed seasonality in visible and near-infrared spectral regions which was linked to occurrences of leaf growth, flowering, berrying, and leaf senescence. The seasonality of spectra differed between species due to different phenologies (evergreen vs. deciduous). Vegetation indices, normalized difference vegetation index (NDVI), moisture stress index (MSI), plant senescence reflectance index (PSRI), and red-edge inflection point (REIP2), showed characteristic seasonal trends. NDVI and PSRI were sensitive to the presence of flowers and berries of lingonberry, while with blueberry the effects were less evident. Off-nadir observations supported differentiating the dwarf shrub species from each other but showed little improvement for detection of flowers and berries. Lingonberry and blueberry can be identified by their spectral signatures if ground reference data are available over the entire growing season. The spectral data measured in this study are reposited in the publicly open SPECCHIO Spectral Information System.Vaccinium vitis-idaeaVaccinium myrtillus

Download Full-text

Use of Landsat images for yield evaluation within a small plot

Plant Soil and Environment ◽

10.17221/515/2014-pse ◽

2014 ◽

Vol 60 (No. 11) ◽

pp. 501-506 ◽

Cited By ~ 6

Author(s):

J. Kumhálová ◽

F. Zemek ◽

P. Novák ◽

O. Brovkina ◽

M. Mayerová

Keyword(s):

Winter Wheat ◽

Water Distribution ◽

Vegetation Indices ◽

Wheat Yield ◽

Moisture Stress ◽

Stress Index ◽

Growth Stages ◽

Landsat Images ◽

Topographic Attributes ◽

Small Plot

Many factors can influence crop yield. One of the most important factors is topography, which can play a crucial role especially in dry years. Plant variability can be monitored by many methods. This paper evaluates the suitability of vegetation indices derived from satellite Landsat 5 TM data in comparison with yield, curvature and topography wetness index over a relatively small field (11.5 ha). Imageries were chosen from the years 2006 and 2010, when oat was grown and from 2005 and 2011, when winter wheat was grown. These images were taken in June in the same growth stage for every crop. It was confirmed that derived indices from Landsat images can be used for comparison with yield and selected topographic attributes and it can explain yield variability, which can be influenced by water distribution during growth stages. Correlation coefficient between moisture stress index and winter wheat yield was –0.816 in the image acquisition date of 4. 6. 2011.

Download Full-text

Integration of a Landsat Time-Series of NBR and Hydrological Modeling to Assess Pinus Pinaster Aiton. Forest Defoliation in South-Eastern Spain

Remote Sensing ◽

10.3390/rs11192291 ◽

2019 ◽

Vol 11 (19) ◽

pp. 2291

Author(s):

Ariza Salamanca ◽

Navarro-Cerrillo ◽

Bonet-García ◽

Palazón ◽

Polo

Keyword(s):

Time Series ◽

Pinus Pinaster ◽

Hydrological Modeling ◽

Potential Evapotranspiration ◽

Moisture Stress ◽

Machine Learning Algorithms ◽

Stress Index ◽

Support Vector ◽

Distributed Hydrological Model ◽

Hydrological Variables

Climate change is increasing the vulnerability of Mediterranean coniferous plantations. Here, we integrate a Landsat time series with a physically-based distributed hydrological model (Watershed Integrated Management in Mediterranean Environments—WiMMed) to examine spatially-explicit relationships between the mortality processes of Pinus pinaster plantations and the hydrological regime, using different spectral indices of vegetation and machine learning algorithms. The Normalized Burn Ratio (NBR) and Moisture Stress Index (MSI) show the highest correlations with defoliation rates. Random Forest was the most accurate model (R2 = 0.79; RMSE = 0.059), showing a high model performance and prediction. Support vector machines and neural networks also demonstrated a high performance (R2 > 0.7). The main hydrological variables selected by the model to explain defoliation were potential evapotranspiration, winter precipitation and maximum summer temperature (lower Out-of-bag error). These results show the importance of hydrological variables involved in evaporation processes, and on the change in the spatial distribution of seasonal rainfall upon the defoliation processes of P. pinaster. These results underpin the importance of integrating temporal remote sensing data and hydrological models to analyze the drivers of forest defoliation and mortality processes in the Mediterranean climate.

Download Full-text

Influence of hemlock woolly adelgid infestation on the physiological and reflectance characteristics of eastern hemlock

Canadian Journal of Forest Research ◽

10.1139/cjfr-2015-0328 ◽

2016 ◽

Vol 46 (3) ◽

pp. 410-426 ◽

Cited By ~ 6

Author(s):

Justin P. Williams ◽

Ryan P. Hanavan ◽

Barrett N. Rock ◽

Subhash C. Minocha ◽

Ernst Linder

Keyword(s):

Remote Sensing ◽

Vegetation Index ◽

Near Infrared ◽

Moisture Stress ◽

Hemlock Woolly Adelgid ◽

Adelges Tsugae ◽

Eastern Hemlock ◽

Stress Index ◽

Compensatory Response ◽

Fluorescence Measurements

The hemlock woolly adelgid (HWA) (Adelges tsugae Annand) is an invasive insect in the eastern United States. Since its initial detection in Richmond, Virginia, in 1951, HWA has spread to half of the eastern hemlock (Tsuga canadensis (L.) Carr.) natural range. Detection of early infestation symptoms via remote sensing requires the knowledge of the changes in reflectance resulting from physiological changes in the host as inflicted by the insect and the selection of equipment with the appropriate sensor characteristics. Laboratory-based reflectance measurements of infested and non-infested hemlock foliage collected from four sites in southern New Hampshire and Maine occurred biweekly over 6 months in 2012 and weekly over 5 weeks in 2013. Vegetation indices (red edge inflection point (REIP), normalized difference vegetation index (NDVI), moisture stress index (MSI), and near infrared (NIR) 3/1 ratio) were associated with concurrent chlorophyll and moisture content data. Infested first-year foliage contained greater concentrations of chlorophyll and moisture, resulting in reduced visible spectral reflectance, greater REIP and NDVI values, and lower MSI and NIR 3/1 values than non-infested foliage. Furthermore, fluorescence measurements indicated greater photosystem function during the early stages of infestation, suggesting a possible compensatory response by hemlock to infestation. Significant differences in reflectance between infested and non-infested foliage were observed in late June and July in the weeks immediately following HWA settlement on new growth. Implementing these observations during remote sensing mission planning may increase the likelihood of detecting early HWA infestation symptoms at landscape scales.

Download Full-text

On the Use of Standardized Multi-Temporal Indices for Monitoring Disturbance and Ecosystem Moisture Stress across Multiple Earth Observation Systems in the Google Earth Engine

Remote Sensing ◽

10.3390/rs13081448 ◽

2021 ◽

Vol 13 (8) ◽

pp. 1448

Author(s):

Tyson L. Swetnam ◽

Stephen R. Yool ◽

Samapriya Roy ◽

Donald A. Falk

Keyword(s):

Time Series ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Moisture Stress ◽

Google Earth ◽

Stress Index ◽

Reference Time ◽

Multi Temporal ◽

Object Part ◽

Index Value

In this work we explore three methods for quantifying ecosystem vegetation responses spatially and temporally using Google’s Earth Engine, implementing an Ecosystem Moisture Stress Index (EMSI) to monitor vegetation health in agricultural, pastoral, and natural landscapes across the entire era of spaceborne remote sensing. EMSI is the multitemporal standard (z) score of the Normalized Difference Vegetation Index (NDVI) given as I, for a pixel (x,y) at the observational period t. The EMSI is calculated as: zxyt = (Ixyt − ?xyT)/?xyT, where the index value of the observational date (Ixyt) is subtracted from the mean (?xyT) of the same date or range of days in a reference time series of length T (in years), divided by the standard deviation (?xyT), during the same day or range of dates in the reference time series. EMSI exhibits high significance (z > |2.0 ± 1.98σ|) across all geographic locations and time periods examined. Our results provide an expanded basis for detection and monitoring: (i) ecosystem phenology and health; (ii) wildfire potential or burn severity; (iii) herbivory; (iv) changes in ecosystem resilience; and (v) change and intensity of land use practices. We provide the code and analysis tools as a research object, part of the findable, accessible, interoperable, reusable (FAIR) data principles.

Download Full-text

Monitoring Crop Water Status and Irrigation Needs Using Multispectral Airborne Sensors

HortScience ◽

10.21273/hortsci.30.4.905d ◽

1995 ◽

Vol 30 (4) ◽

pp. 905D-905

Author(s):

Thomas R. Clarke ◽

M. Susan Moran

Keyword(s):

Water Stress ◽

Near Infrared ◽

Water Status ◽

Canopy Cover ◽

Stress Index ◽

Crop Water ◽

Vegetative Cover ◽

Crop Water Stress Index ◽

Water Stress Index ◽

Subsurface Drip

Water application efficiency can be improved by directly monitoring plant water status rather than depending on soil moisture measurements or modeled ET estimates. Plants receiving sufficient water through their roots have cooler leaves than those that are water-stressed, leading to the development of the Crop Water Stress Index based on hand-held infrared thermometry. Substantial error can occur in partial canopies, however, as exposed hot soil contributes to deceptively warm temperature readings. Mathematically comparing red and near-infrared reflectances provides a measure of vegetative cover, and this information was combined with thermal radiance to give a two-dimensional index capable of detecting water stress even with a low percentage of canopy cover. Thermal, red, and near-infrared images acquired over subsurface drip-irrigated cantaloupe fields demonstrated the method's ability to detect areas with clogged emitters, insufficient irrigation rate, and system water leaks.

Download Full-text

Understanding Vine Hyperspectral Signature through Different Irrigation Plans: A First Step to Monitor Vineyard Water Status

Remote Sensing ◽

10.3390/rs13030536 ◽

2021 ◽

Vol 13 (3) ◽

pp. 536

Author(s):

Eve Laroche-Pinel ◽

Mohanad Albughdadi ◽

Sylvie Duthoit ◽

Véronique Chéret ◽

Jacques Rousseau ◽

...

Keyword(s):

Near Infrared ◽

Water Status ◽

Vegetation Indices ◽

Remote Sensing Data ◽

Short Wave ◽

Spatial And Temporal Scales ◽

Spectral Bands ◽

Main Challenge ◽

Spectral Scale ◽

Grape Varieties

The main challenge encountered by Mediterranean winegrowers is water management. Indeed, with climate change, drought events are becoming more intense each year, dragging the yield down. Moreover, the quality of the vineyards is affected and the level of alcohol increases. Remote sensing data are a potential solution to measure water status in vineyards. However, important questions are still open such as which spectral, spatial, and temporal scales are adapted to achieve the latter. This study aims at using hyperspectral measurements to investigate the spectral scale adapted to measure their water status. The final objective is to find out whether it would be possible to monitor the vine water status with the spectral bands available in multispectral satellites such as Sentinel-2. Four Mediterranean vine plots with three grape varieties and different water status management systems are considered for the analysis. Results show the main significant domains related to vine water status (Short Wave Infrared, Near Infrared, and Red-Edge) and the best vegetation indices that combine these domains. These results give some promising perspectives to monitor vine water status.

Download Full-text

Neural Data-Driven Captioning of Time-Series Line Charts

Proceedings of the International Conference on Advanced Visual Interfaces ◽

10.1145/3399715.3399829 ◽

2020 ◽

Author(s):

Andrea Spreafico ◽

Giuseppe Carenini

Keyword(s):

Time Series ◽

Data Driven ◽

Neural Data

Download Full-text

Assessing Leaf Biomass of Agave sisalana Using Sentinel-2 Vegetation Indices

Remote Sensing ◽

10.3390/rs13020233 ◽

2021 ◽

Vol 13 (2) ◽

pp. 233

Author(s):

Ilja Vuorinne ◽

Janne Heiskanen ◽

Petri K. E. Pellikka

Keyword(s):

Near Infrared ◽

Vegetation Indices ◽

Fibre Production ◽

Additive Models ◽

Leaf Biomass ◽

Ground Vegetation ◽

Perennial Crop ◽

Red Edge ◽

Agave Sisalana ◽

Sentinel 2

Biomass is a principal variable in crop monitoring and management and in assessing carbon cycling. Remote sensing combined with field measurements can be used to estimate biomass over large areas. This study assessed leaf biomass of Agave sisalana (sisal), a perennial crop whose leaves are grown for fibre production in tropical and subtropical regions. Furthermore, the residue from fibre production can be used to produce bioenergy through anaerobic digestion. First, biomass was estimated for 58 field plots using an allometric approach. Then, Sentinel-2 multispectral satellite imagery was used to model biomass in an 8851-ha plantation in semi-arid south-eastern Kenya. Generalised Additive Models were employed to explore how well biomass was explained by various spectral vegetation indices (VIs). The highest performance (explained deviance = 76%, RMSE = 5.15 Mg ha−1) was achieved with ratio and normalised difference VIs based on the green (R560), red-edge (R740 and R783), and near-infrared (R865) spectral bands. Heterogeneity of ground vegetation and resulting background effects seemed to limit model performance. The best performing VI (R740/R783) was used to predict plantation biomass that ranged from 0 to 46.7 Mg ha−1 (mean biomass 10.6 Mg ha−1). The modelling showed that multispectral data are suitable for assessing sisal leaf biomass at the plantation level and in individual blocks. Although these results demonstrate the value of Sentinel-2 red-edge bands at 20-m resolution, the difference from the best model based on green and near-infrared bands at 10-m resolution was rather small.

Download Full-text

Data-driven approach for tailoring facilitation strategies to overcome implementation barriers in community pharmacy

Implementation Science ◽

10.1186/s13012-021-01138-8 ◽

2021 ◽

Vol 16 (1) ◽

Author(s):

Lydia Moussa ◽

Shalom Benrimoj ◽

Katarzyna Musial ◽

Simon Kocbek ◽

Victoria Garcia-Cardenas

Keyword(s):

Random Forest ◽

Community Pharmacy ◽

Implementation Research ◽

Theoretical Domains Framework ◽

Professional Services ◽

Data Driven ◽

Machine Learning Techniques ◽

Community Pharmacies ◽

Continuous Change ◽

Implementation Barriers

Abstract Background Implementation research has delved into barriers to implementing change and interventions for the implementation of innovation in practice. There remains a gap, however, that fails to connect implementation barriers to the most effective implementation strategies and provide a more tailored approach during implementation. This study aimed to explore barriers for the implementation of professional services in community pharmacies and to predict the effectiveness of facilitation strategies to overcome implementation barriers using machine learning techniques. Methods Six change facilitators facilitated a 2-year change programme aimed at implementing professional services across community pharmacies in Australia. A mixed methods approach was used where barriers were identified by change facilitators during the implementation study. Change facilitators trialled and recorded tailored facilitation strategies delivered to overcome identified barriers. Barriers were coded according to implementation factors derived from the Consolidated Framework for Implementation Research and the Theoretical Domains Framework. Tailored facilitation strategies were coded into 16 facilitation categories. To predict the effectiveness of these strategies, data mining with random forest was used to provide the highest level of accuracy. A predictive resolution percentage was established for each implementation strategy in relation to the barriers that were resolved by that particular strategy. Results During the 2-year programme, 1131 barriers and facilitation strategies were recorded by change facilitators. The most frequently identified barriers were a ‘lack of ability to plan for change’, ‘lack of internal supporters for the change’, ‘lack of knowledge and experience’, ‘lack of monitoring and feedback’, ‘lack of individual alignment with the change’, ‘undefined change objectives’, ‘lack of objective feedback’ and ‘lack of time’. The random forest algorithm used was able to provide 96.9% prediction accuracy. The strategy category with the highest predicted resolution rate across the most number of implementation barriers was ‘to empower stakeholders to develop objectives and solve problems’. Conclusions Results from this study have provided a better understanding of implementation barriers in community pharmacy and how data-driven approaches can be used to predict the effectiveness of facilitation strategies to overcome implementation barriers. Tailored facilitation strategies such as these can increase the rate of real-time implementation of innovations in healthcare, leading to an industry that can confidently and efficiently adapt to continuous change.

Download Full-text