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

Johansen, Kasper; Morton, Mitchell J. L.; Malbéteau, Yoann; Aragon, B.; Al-Mashharawi, Samir; Ziliani, Matteo G.; Angel, Yoseline; Fiene, Gabriele; Negrão, Sónia; Mousa, Magdi A. A.; Tester, Mark; McCabe, Matthew F.

doi:10.5194/isprs-archives-xlii-2-w13-407-2019

Cited by 17 publications

(17 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other researchers have also carried out many studies in the field of multisensor data fusion and obtained the same results in studies on the monitoring of crop biomass, such as rice (Cen et al, 2019) and soybean (Maimaitijiang et al, 2020). In addition, different crops have different characteristics, and the same crop will show different characteristics under different growth conditions (Johansen et al, 2019;ten Harkel et al, 2020), which requires the use of different sensors to collect crop information comprehensively and screen out some information most related to biomass. The combination of data from multiple sensors is an effective method to improve the accuracy of biomass estimation.…”

Section: Multisensor Fusionmentioning

confidence: 88%

“…On the one hand, it is difficult to obtain reliable CH data from LiDAR in some cases. Johansen et al (2019) found that dust storms can cause tomato plants to flatten and that once the tomato fruits become large and heavy, the weight may cause the branches to bend downward, thereby reducing the height of the plants. ten Harkel et al (2020) found that potatoes have complex canopy structures and grow on ridges, so it is difficult to visually determine the highest point of a specific position.…”

Section: Crop Heightmentioning

confidence: 99%

See 1 more Smart Citation

Applications of UAS in Crop Biomass Monitoring: A Review

et al. 2021

View full text Add to dashboard Cite

Biomass is an important indicator for evaluating crops. The rapid, accurate and nondestructive monitoring of biomass is the key to smart agriculture and precision agriculture. Traditional detection methods are based on destructive measurements. Although satellite remote sensing, manned airborne equipment, and vehicle-mounted equipment can nondestructively collect measurements, they are limited by low accuracy, poor flexibility, and high cost. As nondestructive remote sensing equipment with high precision, high flexibility, and low-cost, unmanned aerial systems (UAS) have been widely used to monitor crop biomass. In this review, UAS platforms and sensors, biomass indices, and data analysis methods are presented. The improvements of UAS in monitoring crop biomass in recent years are introduced, and multisensor fusion, multi-index fusion, the consideration of features not directly related to monitoring biomass, the adoption of advanced algorithms and the use of low-cost sensors are reviewed to highlight the potential for monitoring crop biomass with UAS. Considering the progress made to solve this type of problem, we also suggest some directions for future research. Furthermore, it is expected that the challenge of UAS promotion will be overcome in the future, which is conducive to the realization of smart agriculture and precision agriculture.

show abstract

Section: Multisensor Fusionmentioning

confidence: 88%

Section: Crop Heightmentioning

confidence: 99%

Applications of UAS in Crop Biomass Monitoring: A Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In addition, machine learning (ML) approach with UAV imagery has been used to estimate biomass of crops including wheat [24], rice [25,26], maize [22], and barley [27]. Except for studies by Moeckel et al [28] and Johansen et al [11,12], we did not identify any studies that used UAVbased time series to predict tomato plant biomass and yield at harvest at the plant level.…”

Section: Introductionmentioning

confidence: 98%

Prediction of plant-level tomato biomass and yield using machine learning with unmanned aerial vehicle imagery

Tatsumi

Igarashi

Mengxue

2021

Preprint

View full text Add to dashboard Cite

Background The objective of this study is twofold. First, ascertain the important variables that predict tomato yields from plant height (PH) and vegetation index (VI) maps. The maps were derived from images taken by unmanned aerial vehicles (UAVs). Second, examine the accuracy of predictions of tomato fresh shoot masses (SM), fruit weights (FW), and the number of fruits (FN) from multiple machine learning algorithms using selected variable sets. To realize our objective, ultra-high-resolution RGB and multispectral images were collected by a UAV on ten days in 2020’s tomato growing season. From these images, 756 total variables, including first- (e.g., average, standard deviation, skewness, range, and maximum) and second-order (e.g., gray-level co-occurrence matrix features and growth rates of PH and VIs) statistics for each plant, were extracted. Several selection algorithms (i.e., Boruta, DALEX, genetic algorithm, least absolute shrinkage and selection operator, and recursive feature elimination) were used to select the variable sets useful for predicting SM, FW, and FN. Random forests, ridge regressions, and support vector machines were used to predict the yield using the top five selected variable sets. Results First-order statistics of PH and VIs collected during the early to mid-fruit formation periods, about one month prior to harvest, were important variables for predicting SM. Similar to the case for SM, variables collected approximately one month prior to harvest were important for predicting FW and FN. Furthermore, variables related to PH were unimportant for prediction. Compared with predictions obtained using only first-order statistics, those obtained using the second-order statistics of VIs were more accurate for FW and FN. Conclusions In addition to basic statistics (e.g., average and standard deviation), we derived second-order statistics of PH and VIs at the plant level using the ultra-high resolution UAV images. Our findings indicated that our variable selection method reduced the number variables needed for tomato yield prediction, improving the efficiency of phenotypic data collection and assisting with the selection of high-yield lines within breeding programs.

show abstract

“…Furthermore, they used the mapped traits to identify tomato plant accessions that performed the best in terms of yield. Johansen et al [12] researched the predictability of fresh shoot mass (SM), number of fruits (FN), and yield mass at harvest using UAV-based imagery and indicated that plant area, border length, width, and length of plant had the highest importance in the random forest approach to modeling of biomass and yield. Candiago et al [13] examined the vegetation vigor of vineyards and tomatoes using three different vegetation indices (VIs) based on orthoimages and demonstrated the great potential of high-resolution UAV data.…”

Section: Introductionmentioning

confidence: 99%

Prediction of plant-level tomato biomass and yield using machine learning with unmanned aerial vehicle imagery

2021

View full text Add to dashboard Cite

Background The objective of this study is twofold. First, ascertain the important variables that predict tomato yields from plant height (PH) and vegetation index (VI) maps. The maps were derived from images taken by unmanned aerial vehicles (UAVs). Second, examine the accuracy of predictions of tomato fresh shoot masses (SM), fruit weights (FW), and the number of fruits (FN) from multiple machine learning algorithms using selected variable sets. To realize our objective, ultra-high-resolution RGB and multispectral images were collected by a UAV on ten days in 2020’s tomato growing season. From these images, 756 total variables, including first- (e.g., average, standard deviation, skewness, range, and maximum) and second-order (e.g., gray-level co-occurrence matrix features and growth rates of PH and VIs) statistics for each plant, were extracted. Several selection algorithms (i.e., Boruta, DALEX, genetic algorithm, least absolute shrinkage and selection operator, and recursive feature elimination) were used to select the variable sets useful for predicting SM, FW, and FN. Random forests, ridge regressions, and support vector machines were used to predict the yield using the top five selected variable sets. Results First-order statistics of PH and VIs collected during the early to mid-fruit formation periods, about one month prior to harvest, were important variables for predicting SM. Similar to the case for SM, variables collected approximately one month prior to harvest were important for predicting FW and FN. Furthermore, variables related to PH were unimportant for prediction. Compared with predictions obtained using only first-order statistics, those obtained using the second-order statistics of VIs were more accurate for FW and FN. The prediction accuracy of SM, FW, and FN by models constructed from all variables (rRMSE = 8.8–28.1%) was better than that from first-order statistics (rRMSE = 10.0–50.1%). Conclusions In addition to basic statistics (e.g., average and standard deviation), we derived second-order statistics of PH and VIs at the plant level using the ultra-high resolution UAV images. Our findings indicated that our variable selection method reduced the number variables needed for tomato yield prediction, improving the efficiency of phenotypic data collection and assisting with the selection of high-yield lines within breeding programs.

show abstract

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

Cited by 17 publications

References 9 publications

Applications of UAS in Crop Biomass Monitoring: A Review

Applications of UAS in Crop Biomass Monitoring: A Review

Prediction of plant-level tomato biomass and yield using machine learning with unmanned aerial vehicle imagery

Prediction of plant-level tomato biomass and yield using machine learning with unmanned aerial vehicle imagery

Contact Info

Product

Resources

About