Above-ground biomass estimation of arable crops using UAV-based SfM photogrammetry

Docampo, María Luz Gil; Arza-García, Marcos; Sanz, Juan Ortiz; Martínez-Rodriguez, Santiago; Marcos-Robles, José Luís; Sastre, Luis

doi:10.1080/10106049.2018.1552322

Cited by 41 publications

(30 citation statements)

References 30 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the other end of the spectrum, it can be very time consuming, labor intensive, and subjective to consistently collect field data suitable for predicting biomass and yield at harvest (Sugiura et al, 2015 ; Holman et al, 2016 ). The divide between space- and ground-based data collection has recently been filled by the use of unmanned aerial vehicles (UAVs), which provide a means for efficient, regular, and flexible collection of imagery at very high spatial resolutions, suitable for regular assessment of crops, their properties, and stress factors (Gil-Docampo et al, 2018 ). Deployment of UAVs for data collection also reduces the requirement for human-based on-site observations (and potential for investigator bias), increases safety and access, and facilitates the implementation of management practices in the agricultural sector (Shi et al, 2016 ; Barbedo, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

Predicting Biomass and Yield in a Tomato Phenotyping Experiment Using UAV Imagery and Random Forest

Johansen

Morton

Malbéteau

et al. 2020

Front. Artif. Intell.

View full text Add to dashboard Cite

Biomass and yield are key variables for assessing the production and performance of agricultural systems. Modeling and predicting the biomass and yield of individual plants at the farm scale represents a major challenge in precision agriculture, particularly when salinity and other abiotic stresses may play a role. Here, we evaluate a diversity panel of the wild tomato species ( Solanum pimpinellifolium ) through both field and unmanned aerial vehicle (UAV)-based phenotyping of 600 control and 600 salt-treated plants. The study objective was to predict fresh shoot mass, tomato fruit numbers, and yield mass at harvest based on a range of variables derived from the UAV imagery. UAV-based red–green–blue (RGB) imageries collected 1, 2, 4, 6, 7, and 8 weeks before harvest were also used to determine if prediction accuracies varied between control and salt-treated plants. Multispectral UAV-based imagery was also collected 1 and 2 weeks prior to harvest to further explore predictive insights. In order to estimate the end of season biomass and yield, a random forest machine learning approach was implemented using UAV-imagery-derived predictors as input variables. Shape features derived from the UAV, such as plant area, border length, width, and length, were found to have the highest importance in the predictions, followed by vegetation indices and the entropy texture measure. The multispectral UAV imagery collected 2 weeks prior to harvest produced the highest explained variances for fresh shoot mass (87.95%), fruit numbers (63.88%), and yield mass per plant (66.51%). The RGB UAV imagery produced very similar results to those of the multispectral UAV dataset, with the explained variance reducing as a function of increasing time to harvest. The results showed that predicting the yield of salt-stressed plants produced higher accuracies when the models excluded control plants, whereas predicting the yield of control plants was not affected by the inclusion of salt-stressed plants within the models. This research demonstrates that it is possible to predict the average biomass and yield up to 8 weeks prior to harvest within 4.23% of field-based measurements and up to 4 weeks prior to harvest at the individual plant level. Results from this work may be useful in providing guidance for yield forecasting of healthy and salt-stressed tomato plants, which in turn may inform growing practices, logistical planning, and sales operations.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting Biomass and Yield in a Tomato Phenotyping Experiment Using UAV Imagery and Random Forest

Johansen

Morton

Malbéteau

et al. 2020

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…While field-based collection of data suitable for predicting biomass and yield at the time of harvest is very time-consuming, labor-intensive and subjective, especially for collection of timeseries data that demand repetitive collection procedures, Unmanned Aerial Vehicle (UAV) based imagery can be collected efficiently and regularly (Gil-Docampo et al, 2018). Recent developments in UAV technology and miniaturized sensors provide the capability to obtain imagery at high temporal and spatial resolutions suitable for regular assessment of individual tomato plants and their properties.…”

Section: Introductionmentioning

confidence: 99%

Predicting Biomass and Yield at Harvest of Salt-Stressed Tomato Plants Using Uav Imagery

Johansen

Morton

Malbéteau

et al. 2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Biomass and yield are important variables used for assessing agricultural production. However, these variables are difficult to estimate for individual plants at the farm scale and may be affected by abiotic stressors such as salinity. In this study, the wild tomato species, Solanum pimpinellifolium, was evaluated through field and UAV-based assessment of 600 control and 600 salt-treated plants. The aim of this research was to determine, if UAV-based imagery, collected one, two, four, six, seven and eight weeks before harvest could predict fresh shoot mass, tomato fruit numbers, and yield mass at harvest and if predictions varied for control and salttreated plants. A Random Forest approach was used to model biomass and yield. The results showed that shape features such as plant area, border length, width and length had the highest importance in the random forest models. A week prior to harvest, the explained variance of fresh shoot mass, number of fruits and yield mass were 86.60%, 59.46% and 61.09%, respectively. The explained variance was reduced as a function of time to harvest. Separate models may be required for predicting yield of salt-stressed plants, whereas the prediction of yield for control plants was less affected if the model included salt-stressed plants. This research demonstrates that it is possible to predict biomass and yield of tomato plants up to four weeks prior to harvest, and potentially earlier in the absence of severe weather events.

show abstract

“…To date, phenotyping is labor and time-intensive and is also largely affected by human errors and biases. For these reasons, robotic devices and aerial vehicles are becoming a big opportunity to increase the accuracy of the phenotypic estimations, which in turn can be used in statistical models [ 48 , 49 , 50 , 51 , 52 ]. The development of statistical models capable of accurately predict marker effects has led to the breakthrough of GS increasing the rate of genetic gain per unit of time.…”

Section: Potential Of Gs In Plantmentioning

confidence: 99%

“…The effectiveness of GEBVs for prediction was mainly demonstrated in polyploid wheat [ 27 , 52 , 53 , 54 , 55 , 56 , 57 ] but studies are also available for diploids rice [ 54 , 58 ], barley [ 59 , 63 ], soybean [ 60 , 61 ], maize [ 27 , 62 ] and tomato [ 22 , 23 , 24 , 25 ]. Lorenzana and Bernardo [ 59 ] obtained GEBV accuracies between 0.64 and 0.83 using 150 DHs (doubled-haploid) barley lines and 223 Restriction Fragment Length Polymorphism (RFLP) markers to improve grain yield and amylase activity.…”

Section: Lesson From Other Speciesmentioning

confidence: 99%

Accelerating Tomato Breeding by Exploiting Genomic Selection Approaches

Cappetta

Andolfo

Matteo

et al. 2020

Plants

View full text Add to dashboard Cite

Genomic selection (GS) is a predictive approach that was built up to increase the rate of genetic gain per unit of time and reduce the generation interval by utilizing genome-wide markers in breeding programs. It has emerged as a valuable method for improving complex traits that are controlled by many genes with small effects. GS enables the prediction of the breeding value of candidate genotypes for selection. In this work, we address important issues related to GS and its implementation in the plant context with special emphasis on tomato breeding. Genomic constraints and critical parameters affecting the accuracy of prediction such as the number of markers, statistical model, phenotyping and complexity of trait, training population size and composition should be carefully evaluated. The comparison of GS approaches for facilitating the selection of tomato superior genotypes during breeding programs is also discussed. GS applied to tomato breeding has already been shown to be feasible. We illustrated how GS can improve the rate of gain in elite line selection, and descendent and backcross schemes. The GS schemes have begun to be delineated and computer science can provide support for future selection strategies. A new promising breeding framework is beginning to emerge for optimizing tomato improvement procedures.

show abstract

Above-ground biomass estimation of arable crops using UAV-based SfM photogrammetry

Cited by 41 publications

References 30 publications

Predicting Biomass and Yield in a Tomato Phenotyping Experiment Using UAV Imagery and Random Forest

Predicting Biomass and Yield in a Tomato Phenotyping Experiment Using UAV Imagery and Random Forest

Predicting Biomass and Yield at Harvest of Salt-Stressed Tomato Plants Using Uav Imagery

Accelerating Tomato Breeding by Exploiting Genomic Selection Approaches

Contact Info

Product

Resources

About