Detection of diurnal variation in orchard canopy water content using MODIS/ASTER airborne simulator (MASTER) data

Cheng, Tao; Riaño, David; Koltunov, Alexander; Whiting, Michael L.; Ustin, Susan L.; Rodriguez, Jenna

doi:10.1016/j.rse.2012.12.024

Cited by 33 publications

(20 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The more stratified the data, the closer a random sample is to the population dataset. However, sampling efficiency and sample representativeness are reduced when the number of strata is less than 30 [37,38]. Every 7-10 days represents one soybean growth period, for a total of approximately 16 periods throughout the whole growth process.…”

Section: Data Collectionmentioning

confidence: 99%

Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models

et al. 2017

View full text Add to dashboard Cite

Leaf area index (LAI) is an important indicator of plant growth and yield that can be monitored by remote sensing. Several models were constructed using datasets derived from SRS and STR sampling methods to determine the optimal model for soybean (multiple strains) LAI inversion for the whole crop growth period and a single growth period. Random forest (RF), artificial neural network (ANN), and support vector machine (SVM) regression models were compared with a partial least-squares regression (PLS) model. The RF model yielded the highest precision, accuracy, and stability with V-R 2 , SD R 2 , V-RMSE, and SD RMSE values of 0.741, 0.031, 0.106, and 0.005, respectively, over the whole growth period based on STR sampling. The ANN model had the highest precision, accuracy, and stability (0.452, 0.132, 0.086, and 0.009, respectively) over a single growth phase based on STR sampling. The precision, accuracy, and stability of the RF, ANN, and SVM models were improved by inclusion of STR sampling. The RF model is suitable for estimating LAI when sample plots and variation are relatively large (i.e., the whole growth period or more than one growth period). The ANN model is more appropriate for estimating LAI when sample plots and variation are relatively low (i.e., a single growth period).

show abstract

Section: Data Collectionmentioning

confidence: 99%

Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Vegetation indices derived from various mathematical combinations (i.e., ratio, difference, normalized difference) of hyperspectral and multispectral data have shown promise as tools for agricultural application, including determining canopy water content and water stress of crops [7] [8] [9], assessing insect and disease infestations [10] [11] [12] [13] [14], differentiating crops from weeds [15]- [20], and assessing nutrient status of plants [21] [22]. The advantages of using vegetation indices over single wavebands include enhancing differences in the spectral properties of plants, while diminishing the influence of relief, nonphotosynthesizing elements of plants, atmosphere, soil background, shadow, and viewing and illumination geometry on spectral data [23] [24].…”

Section: Introductionmentioning

confidence: 99%

Using Vegetation Indices as Input into Random Forest for Soybean and Weed Classification

Fletcher¹

2016

AJPS

View full text Add to dashboard Cite

Weed management is a major component of a soybean (Glycine max L.) production system; thus, managers need tools to help them distinguish soybean from weeds. Vegetation indices derived from light reflectance properties of plants have shown promise as tools to enhance differences among plants. The objective of this study was to evaluate normalized difference vegetation indices derived from multispectral leaf reflectance data as input into random forest machine learner to differentiate soybean and three broad leaf weeds: Palmer amaranth (Amaranthus palmeri L.), redroot pigweed (A. retroflexus L.), and velvetleaf (Abutilon theophrasti Medik). Leaf reflectance measurements were acquired from plants grown in two separate greenhouse experiments conducted in 2014. Twelve normalized difference vegetation indices were derived from the reflectance measurements, including advanced, green, greenred, green-blue, and normalized difference vegetation indices, shortwave infrared water stress indices, normalized difference pigment and red edge indices, and structure insensitive pigment index. Using the twelve vegetation indices as input variables, the conditional inference version of random forest (cforest) readily distinguished soybean and velvetleaf from the two pigweeds (Palmer amaranth and redroot pigweed) and from each other with classification accuracies ranging from 93.3% to 100%. The greatest errors were observed between the two pigweed classes, with classification accuracies ranging from 70% to 93.3%. Results suggest combining them into one class to increase classification accuracy. Vegetation indices results were equivalent to or slightly better than results obtained with sixteen multispectral bands used as input data into cforest. This research further supports using vegetation indices and machine learning algorithms such as cforest as decision support tools for weed identification.

show abstract

“…Plant reflectance properties in the red and near infrared regions are especially recruited for differentiating soil, water and vegetation with vegetation indices (Glenn et al, 2008). Vegetation indices can be used to estimate vegetation water content (Cheng et al, 2006, based on gravimetric or leaf water content (Cheng et al, 2011, Cheng et al, 2013, equivalent water thickness (EWT; water depth/per pixel; knowledge of pixel area provides the volume estimate), changes which are detectable in the short wave infrared region (1.1-2.5 μm), and evapotranspiration processes by including temperature from thermal infrared measurements (Glenn et al, 2010, Nagler et al, 2005a, Nagler et al, 2005b, thus together, identifying agricultural regions receiving excess or insufficient water supplies. Plant physiology and thus reflectance properties respond differently depending upon the time of year, crop type, and management strategies.…”

Section: Monitoring Crop Canopies and Water Stressmentioning

confidence: 99%

Food, water, and fault lines: Remote sensing opportunities for earthquake-response management of agricultural water

Rodriguez

Ustin

Sandoval-Solís

et al. 2016

Science of The Total Environment

Self Cite

View full text Add to dashboard Cite

Earthquakes often cause destructive and unpredictable changes that can affect local hydrology (e.g. groundwater elevation or reduction) and thus disrupt land uses and human activities. Prolific agricultural regions overlie seismically active areas, emphasizing the importance to improve our understanding and monitoring of hydrologic and agricultural systems following a seismic event. A thorough data collection is necessary for adequate postearthquake crop management response; however, the large spatial extent of earthquake's impact makes challenging the collection of robust data sets for identifying locations and magnitude of these impacts. Observing hydrologic responses to earthquakes is not a novel concept, yet there is a lack of methods and tools for assessing earthquake's impacts upon the regional hydrology and agricultural systems. The objective of this paper is to describe how remote sensing imagery, methods and tools allow detecting crop responses and damage incurred after earthquakes because a change in the regional hydrology. Many remote sensing datasets are long archived with extensive coverage and with well-documented methods to assess plant-water relations. We thus connect remote sensing of plant water relations to its utility in agriculture using a post-earthquake agrohydrologic remote sensing (PEARS) framework; specifically in agro-hydrologic relationships associated with recent earthquake events that will lead to improved water management.© 2016 Elsevier B.V. All rights reserved. Keywords:Agro-hydrology Disaster management Monitoring Plant-water relations Post-earthquake agrohydrologic remote sensing (PEARS) Remote sensing Background, scope & needEarthquake events threaten food security, resource management and human life, and are observed to be steadily increasing (Ellsworth, 2013). As observed earthquake events continue to increase, it is important to explore and improve response and recovery strategies. Infrastructural damages, especially in urban environments, are at the forefront of research in remote sensing of earthquake-associated damage. Agricultural environments also face catastrophic impacts, often due to adverse hydrologic behavior following the event. The earthquake-water linkage poses particular threats to agricultural productivity, yet difficulty lies in predicting the location, destructiveness, and extent of damage. While effects of earthquake-induced hydrologic changes on crops remain largely unexplored, remote sensing of crop water relations provide a suite of tools to monitor responses and to mitigate crop loss. Remote sensing can address these challenges with archived imagery that has extensive spatial coverage. There are conceptual models that explicitly walk through remote sensing in disaster management (Joyce et al., 2009b) and remote sensing of post-earthquake urban damage (Eguchi et al., 2003) -leaving a gap at the interface of post-earthquake remote sensing of agricultural impacts. We therefore draw attention to current research in understanding earthquake impacts on agric...

show abstract

Detection of diurnal variation in orchard canopy water content using MODIS/ASTER airborne simulator (MASTER) data

Cited by 33 publications

References 68 publications

Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models

Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models

Using Vegetation Indices as Input into Random Forest for Soybean and Weed Classification

Food, water, and fault lines: Remote sensing opportunities for earthquake-response management of agricultural water

Contact Info

Product

Resources

About