Publications : AgAID Institute

1.

Ranjan Sapkota; Dawood Ahmed; Manoj Karkee

Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments Journal Article

In: Artificial Intelligence in Agriculture, vol. 13, pp. 84–99, 2024, ISSN: 2589-7217.

Abstract | Links | BibTeX | Tags: Artificial intelligence, Automation, Deep learning, Machine Learning, Machine vision, Mask R-CNN, Robotics, YOLOv8

@article{sapkota_comparing_2024,

title = {Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments},

author = {Ranjan Sapkota and Dawood Ahmed and Manoj Karkee},

url = {https://www.sciencedirect.com/science/article/pii/S258972172400028X},

doi = {10.1016/j.aiia.2024.07.001},

issn = {2589-7217},

year  = {2024},

date = {2024-09-01},

urldate = {2024-09-01},

journal = {Artificial Intelligence in Agriculture},

volume = {13},

pages = {84\textendash99},

abstract = {Instance segmentation, an important image processing operation for automation in agriculture, is used to precisely delineate individual objects of interest within images, which provides foundational information for various automated or robotic tasks such as selective harvesting and precision pruning. This study compares the one-stage YOLOv8 and the two-stage Mask R-CNN machine learning models for instance segmentation under varying orchard conditions across two datasets. Dataset 1, collected in dormant season, includes images of dormant apple trees, which were used to train multi-object segmentation models delineating tree branches and trunks. Dataset 2, collected in the early growing season, includes images of apple tree canopies with green foliage and immature (green) apples (also called fruitlet), which were used to train single-object segmentation models delineating only immature green apples. The results showed that YOLOv8 performed better than Mask R-CNN, achieving good precision and near-perfect recall across both datasets at a confidence threshold of 0.5. Specifically, for Dataset 1, YOLOv8 achieved a precision of 0.90 and a recall of 0.95 for all classes. In comparison, Mask R-CNN demonstrated a precision of 0.81 and a recall of 0.81 for the same dataset. With Dataset 2, YOLOv8 achieved a precision of 0.93 and a recall of 0.97. Mask R-CNN, in this single-class scenario, achieved a precision of 0.85 and a recall of 0.88. Additionally, the inference times for YOLOv8 were 10.9 ms for multi-class segmentation (Dataset 1) and 7.8 ms for single-class segmentation (Dataset 2), compared to 15.6 ms and 12.8 ms achieved by Mask R-CNN's, respectively. These findings show YOLOv8's superior accuracy and efficiency in machine learning applications compared to two-stage models, specifically Mask-R-CNN, which suggests its suitability in developing smart and automated orchard operations, particularly when real-time applications are necessary in such cases as robotic harvesting and robotic immature green fruit thinning.},

keywords = {Artificial intelligence, Automation, Deep learning, Machine Learning, Machine vision, Mask R-CNN, Robotics, YOLOv8},

pubstate = {published},

tppubtype = {article}

}

Close

Instance segmentation, an important image processing operation for automation in agriculture, is used to precisely delineate individual objects of interest within images, which provides foundational information for various automated or robotic tasks such as selective harvesting and precision pruning. This study compares the one-stage YOLOv8 and the two-stage Mask R-CNN machine learning models for instance segmentation under varying orchard conditions across two datasets. Dataset 1, collected in dormant season, includes images of dormant apple trees, which were used to train multi-object segmentation models delineating tree branches and trunks. Dataset 2, collected in the early growing season, includes images of apple tree canopies with green foliage and immature (green) apples (also called fruitlet), which were used to train single-object segmentation models delineating only immature green apples. The results showed that YOLOv8 performed better than Mask R-CNN, achieving good precision and near-perfect recall across both datasets at a confidence threshold of 0.5. Specifically, for Dataset 1, YOLOv8 achieved a precision of 0.90 and a recall of 0.95 for all classes. In comparison, Mask R-CNN demonstrated a precision of 0.81 and a recall of 0.81 for the same dataset. With Dataset 2, YOLOv8 achieved a precision of 0.93 and a recall of 0.97. Mask R-CNN, in this single-class scenario, achieved a precision of 0.85 and a recall of 0.88. Additionally, the inference times for YOLOv8 were 10.9 ms for multi-class segmentation (Dataset 1) and 7.8 ms for single-class segmentation (Dataset 2), compared to 15.6 ms and 12.8 ms achieved by Mask R-CNN's, respectively. These findings show YOLOv8's superior accuracy and efficiency in machine learning applications compared to two-stage models, specifically Mask-R-CNN, which suggests its suitability in developing smart and automated orchard operations, particularly when real-time applications are necessary in such cases as robotic harvesting and robotic immature green fruit thinning.

Close

2.

Dawood Ahmed, Ranjan Sapkota, Martin Churuvija, Matthew Whiting, Manoj Karkee

Slicing-Aided Hyper Inference for Enhanced Fruit Bud Detection and Counting in Apple Orchards during Dormant Season Proceedings Article

In: ASABE, 2024.

Abstract | Links | BibTeX | Tags:

@inproceedings{noauthor_slicing-aided_nodateb,

title = {Slicing-Aided Hyper Inference for Enhanced Fruit Bud Detection and Counting in Apple Orchards during Dormant Season},

author = {Dawood Ahmed, Ranjan Sapkota, Martin Churuvija, Matthew Whiting, Manoj Karkee},

url = {https://doi.org/10.13031/aim.202401055},

year  = {2024},

date = {2024-08-02},

publisher = {ASABE},

abstract = {To meet the global food demand amidst the growing population, there‘s a critical need to augment productivity in the specialty crop industry. However, workforce shortage in agriculture presents a significant challenge to increasing agricultural productivity, emphasizing the need for automating various farm operations such as harvesting, canopy management, and crop-load management practices. A critical aspect of crop-load management is determining existing crop-load along with target yield, which can be used for optimizing crop-load in orchards. Buds, the initial phase of the flowering and fruiting process, are critical for early crop-load estimation (number of fruiting sites per branch or tree) and can facilitate informed pruning decisions to achieve the desired crop-load. Yet, the detection of these buds poses a huge challenge due to their miniature size and variable environmental conditions (including lighting) of commercial orchards. This research explores the performances of a Convolutional Neural Network (CNN) model and a Detection Transformer (DETR) model in detecting fruiting buds in apple orchards, using standard inference and a hyper inferencing technique. Additionally, the system quantifies buds and employs an association algorithm to correlate each bud to its respective branch, facilitating the estimation of the number of buds per branch. Despite the challenges due to the size of buds and environmental complexity, the proposed system demonstrated precision of 80.2 %, recall of 80.1 %, and f1-score of 80.15 % in detecting fruit buds, using a YOLOv8 model. The use of the Slicing Aided Hyper Inferencing Technique improved the overall recall score of the model. Additionally, the system quantified buds in a frame for the most salient branch using the branch-bud association with an accuracy of 73%. This study demonstrated a promising workflow in detecting and counting fruiting buds in a dynamic orchard environment to facilitate current manual pruning operation as well as future studies on automated pruning.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Close

To meet the global food demand amidst the growing population, there‘s a critical need to augment productivity in the specialty crop industry. However, workforce shortage in agriculture presents a significant challenge to increasing agricultural productivity, emphasizing the need for automating various farm operations such as harvesting, canopy management, and crop-load management practices. A critical aspect of crop-load management is determining existing crop-load along with target yield, which can be used for optimizing crop-load in orchards. Buds, the initial phase of the flowering and fruiting process, are critical for early crop-load estimation (number of fruiting sites per branch or tree) and can facilitate informed pruning decisions to achieve the desired crop-load. Yet, the detection of these buds poses a huge challenge due to their miniature size and variable environmental conditions (including lighting) of commercial orchards. This research explores the performances of a Convolutional Neural Network (CNN) model and a Detection Transformer (DETR) model in detecting fruiting buds in apple orchards, using standard inference and a hyper inferencing technique. Additionally, the system quantifies buds and employs an association algorithm to correlate each bud to its respective branch, facilitating the estimation of the number of buds per branch. Despite the challenges due to the size of buds and environmental complexity, the proposed system demonstrated precision of 80.2 %, recall of 80.1 %, and f1-score of 80.15 % in detecting fruit buds, using a YOLOv8 model. The use of the Slicing Aided Hyper Inferencing Technique improved the overall recall score of the model. Additionally, the system quantified buds in a frame for the most salient branch using the branch-bud association with an accuracy of 73%. This study demonstrated a promising workflow in detecting and counting fruiting buds in a dynamic orchard environment to facilitate current manual pruning operation as well as future studies on automated pruning.

Close

3.

Mohsen Farajijalal, Samira Malek, Arash Toudeshki, Joshua H. Viers, Reza Ehsani

Data-Driven Model to Improve Mechanical Harvesters for Nut Trees Proceedings Article

In: ASABE, 2024.

Abstract | Links | BibTeX | Tags:

4.

Alex W. Kirkpatrick; Amanda D. Boyd; Jay D. Hmielowski

Who shares about AI? Media exposure, psychological proximity, performance expectancy, and information sharing about artificial intelligence online Journal Article

In: AI & SOCIETY, 2024, ISSN: 1435-5655.

Abstract | Links | BibTeX | Tags: Artificial intelligence, Information sharing, Media exposure, Psychological distance, Public engagement with science and technology

5.

Shubhomoy Das; Md Rakibul Islam; Nitthilan Kannappan Jayakodi; Janardhan Rao Doppa

Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning Journal Article

In: Journal of Artificial Intelligence Research, vol. 80, pp. 127–170, 2024, ISSN: 1076-9757.

Abstract | Links | BibTeX | Tags: knowledge discovery, Machine Learning

@article{das_effectiveness_2024,

title = {Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning},

author = {Shubhomoy Das and Md Rakibul Islam and Nitthilan Kannappan Jayakodi and Janardhan Rao Doppa},

url = {https://www.jair.org/index.php/jair/article/view/14741},

doi = {10.1613/jair.1.14741},

issn = {1076-9757},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-01},

journal = {Journal of Artificial Intelligence Research},

volume = {80},

pages = {127\textendash170},

abstract = {Anomaly detection (AD) task corresponds to identifying the true anomalies among a given set of data instances. AD algorithms score the data instances and produce a ranked list of candidate anomalies. The ranked list of anomalies is then analyzed by a human to discover the true anomalies. Ensemble of tree-based anomaly detectors trained in an unsupervised manner and scoring based on uniform weights for ensembles are shown to work well in practice. However, the manual process of analysis can be laborious for the human analyst when the number of false-positives is very high. Therefore, in many real-world AD applications including computer security and fraud prevention, the anomaly detector must be configurable by the human analyst to minimize the effort on false positives. One important way to configure the detector is by providing true labels (nominal or anomaly) for a few instances. Recent work on active anomaly discovery has shown that greedily querying the top-scoring instance and tuning the weights of ensembles based on label feedback allows us to quickly discover true anomalies. 

This paper makes four main contributions to improve the state-of-the-art in anomaly discovery using tree-based ensembles. First, we provide an important insight that explains the practical successes of unsupervised tree-based ensembles and active learning based on greedy query selection strategy. We also show empirical results on real-world data to support our insights and theoretical analysis to support active learning. Second, we develop a novel batch active learning algorithm to improve the diversity of discovered anomalies based on a formalism called compact description to describe the discovered anomalies. Third, we develop a novel active learning algorithm to handle streaming data setting. We present a data drift detection algorithm that not only detects the drift robustly, but also allows us to take corrective actions to adapt the anomaly detector in a principled manner. Fourth, we present extensive experiments to evaluate our insights and our tree-based active anomaly discovery algorithms in both batch and streaming data settings. Our results show that active learning allows us to discover significantly more anomalies than state-of-the-art unsupervised baselines, our batch active learning algorithm discovers diverse anomalies, and our algorithms under the streaming-data setup are competitive with the batch setup.},

keywords = {knowledge discovery, Machine Learning},

pubstate = {published},

tppubtype = {article}

}

Close

Anomaly detection (AD) task corresponds to identifying the true anomalies among a given set of data instances. AD algorithms score the data instances and produce a ranked list of candidate anomalies. The ranked list of anomalies is then analyzed by a human to discover the true anomalies. Ensemble of tree-based anomaly detectors trained in an unsupervised manner and scoring based on uniform weights for ensembles are shown to work well in practice. However, the manual process of analysis can be laborious for the human analyst when the number of false-positives is very high. Therefore, in many real-world AD applications including computer security and fraud prevention, the anomaly detector must be configurable by the human analyst to minimize the effort on false positives. One important way to configure the detector is by providing true labels (nominal or anomaly) for a few instances. Recent work on active anomaly discovery has shown that greedily querying the top-scoring instance and tuning the weights of ensembles based on label feedback allows us to quickly discover true anomalies.
This paper makes four main contributions to improve the state-of-the-art in anomaly discovery using tree-based ensembles. First, we provide an important insight that explains the practical successes of unsupervised tree-based ensembles and active learning based on greedy query selection strategy. We also show empirical results on real-world data to support our insights and theoretical analysis to support active learning. Second, we develop a novel batch active learning algorithm to improve the diversity of discovered anomalies based on a formalism called compact description to describe the discovered anomalies. Third, we develop a novel active learning algorithm to handle streaming data setting. We present a data drift detection algorithm that not only detects the drift robustly, but also allows us to take corrective actions to adapt the anomaly detector in a principled manner. Fourth, we present extensive experiments to evaluate our insights and our tree-based active anomaly discovery algorithms in both batch and streaming data settings. Our results show that active learning allows us to discover significantly more anomalies than state-of-the-art unsupervised baselines, our batch active learning algorithm discovers diverse anomalies, and our algorithms under the streaming-data setup are competitive with the batch setup.

Close

6.

Mohammed Amine Gharsallaoui; Bhupinderjeet Singh; Supriya Savalkar; Aryan Deshwal; Yan Yan; Ananth Kalyanaraman; Kirti Rajagopalan; Janardhan Rao Doppa

Streamflow Prediction with Uncertainty Quantification for Water Management: A Constrained Reasoning and Learning Approach Miscellaneous

2024, (arXiv:2406.00133 [cs]).

Abstract | Links | BibTeX | Tags: Computer Science - Artificial Intelligence, Computer Science - Machine Learning

7.

Deanna Flynn; Abhinav Jain; Heather Knight; Cristina G. Wilson; Cindy Grimm

Uncovering implementable dormant pruning decisions from three different stakeholder perspectives Miscellaneous

2024, (arXiv:2405.04030 [cs]).

Abstract | Links | BibTeX | Tags: Computer Science - Robotics

@misc{flynn_uncovering_2024,

title = {Uncovering implementable dormant pruning decisions from three different stakeholder perspectives},

author = {Deanna Flynn and Abhinav Jain and Heather Knight and Cristina G. Wilson and Cindy Grimm},

url = {http://arxiv.org/abs/2405.04030},

doi = {10.48550/arXiv.2405.04030},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-01},

publisher = {arXiv},

abstract = {Dormant pruning, or the removal of unproductive portions of a tree while a tree is not actively growing, is an important orchard task to help maintain yield, requiring years to build expertise. Because of long training periods and an increasing labor shortage in agricultural jobs, pruning could benefit from robotic automation. However, to program robots to prune branches, we first need to understand how pruning decisions are made, and what variables in the environment (e.g., branch size and thickness) we need to capture. Working directly with three pruning stakeholders \textendash horticulturists, growers, and pruners \textendash we find that each group of human experts approaches pruning decision-making differently. To capture this knowledge, we present three studies and two extracted pruning protocols from field work conducted in Prosser, Washington in January 2022 and 2023. We interviewed six stakeholders (two in each group) and observed pruning across three cultivars \textendash Bing Cherries, Envy Apples, and Jazz Apples \textendash and two tree architectures \textendash Upright Fruiting Offshoot and V-Trellis. Leveraging participant interviews and video data, this analysis uses grounded coding to extract pruning terminology, discover horticultural contexts that influence pruning decisions, and find implementable pruning heuristics for autonomous systems. The results include a validated terminology set, which we offer for use by both pruning stakeholders and roboticists, to communicate general pruning concepts and heuristics. The results also highlight seven pruning heuristics utilizing this terminology set that would be relevant for use by future autonomous robot pruning systems, and characterize three discovered horticultural contexts (i.e., environmental management, crop-load management, and replacement wood) across all three cultivars.},

note = {arXiv:2405.04030 [cs]},

keywords = {Computer Science - Robotics},

pubstate = {published},

tppubtype = {misc}

}

Close

8.

Rosalinda Garcia; Patricia Morreale; Gail Verdi; Heather Garcia; Geraldine Jimena Noa; Spencer P. Madsen; Maria Jesus Alzugaray-Orellana; Elizabeth Li; Margaret Burnett

The Matchmaker Inclusive Design Curriculum: A Faculty-Enabling Curriculum to Teach Inclusive Design Throughout Undergraduate CS Proceedings Article

In: Proceedings of the CHI Conference on Human Factors in Computing Systems, pp. 1–22, Association for Computing Machinery, New York, NY, USA, 2024, ISBN: 9798400703300.

Abstract | Links | BibTeX | Tags:

9.

Adrienne M. Marshall; John T. Abatzoglou; Stefan Rahimi; Dennis P. Lettenmaier; Alex Hall

California’s 2023 snow deluge: Contextualizing an extreme snow year against future climate change Journal Article

In: Proceedings of the National Academy of Sciences, vol. 121, no. 20, pp. e2320600121, 2024, (Publisher: Proceedings of the National Academy of Sciences).

Abstract | Links | BibTeX | Tags:

@article{marshall_californias_2024,

title = {California’s 2023 snow deluge: Contextualizing an extreme snow year against future climate change},

author = {Adrienne M. Marshall and John T. Abatzoglou and Stefan Rahimi and Dennis P. Lettenmaier and Alex Hall},

url = {https://www.pnas.org/doi/abs/10.1073/pnas.2320600121},

doi = {10.1073/pnas.2320600121},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-01},

journal = {Proceedings of the National Academy of Sciences},

volume = {121},

number = {20},

pages = {e2320600121},

abstract = {The increasing prevalence of low snow conditions in a warming climate has attracted substantial attention in recent years, but a focus exclusively on low snow leaves high snow years relatively underexplored. However, these large snow years are hydrologically and economically important in regions where snow is critical for water resources. Here, we introduce the term “snow deluge” and use anomalously high snowpack in California’s Sierra Nevada during the 2023 water year as a case study. Snow monitoring sites across the state had a median 41 y return interval for April 1 snow water equivalent (SWE). Similarly, a process-based snow model showed a 54 y return interval for statewide April 1 SWE (90% CI: 38 to 109 y). While snow droughts can result from either warm or dry conditions, snow deluges require both cool and wet conditions. Relative to the last century, cool-season temperature and precipitation during California’s 2023 snow deluge were both moderately anomalous, while temperature was highly anomalous relative to recent climatology. Downscaled climate models in the Shared Socioeconomic Pathway-370 scenario indicate that California snow deluges\textemdashwhich we define as the 20 y April 1 SWE event\textemdashare projected to decline with climate change (58% decline by late century), although less so than median snow years (73% decline by late century). This pattern occurs across the western United States. Changes to snow deluge, and discrepancies between snow deluge and median snow year changes, could impact water resources and ecosystems. Understanding these changes is therefore critical to appropriate climate adaptation.},

note = {Publisher: Proceedings of the National Academy of Sciences},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Close

10.

Victor Blanco; Lee Kalcsits

Relating microtensiometer-based trunk water potential with sap flow, canopy temperature, and trunk and fruit diameter variations for irrigated ‘Honeycrisp’ apple Journal Article

In: Frontiers in Plant Science, vol. 15, 2024, ISSN: 1664-462X, (Publisher: Frontiers).

Abstract | Links | BibTeX | Tags: Continuous measurements, fruit growth, Plant-based sensors, Precision irrigation, Tree water status indicators, water potential

@article{blanco_relating_2024,

title = {Relating microtensiometer-based trunk water potential with sap flow, canopy temperature, and trunk and fruit diameter variations for irrigated ‘Honeycrisp’ apple},

author = {Victor Blanco and Lee Kalcsits},

url = {https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2024.1393028/full},

doi = {10.3389/fpls.2024.1393028},

issn = {1664-462X},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-01},

journal = {Frontiers in Plant Science},

volume = {15},

abstract = {\<p\>Instrumentation plays a key role in modern horticulture. Thus, the microtensiomenter, a new plant-based sensor that continuously monitors trunk water potential (Ψ$_textrmtrunk$) can help in irrigation management decisions. To compare the response of the Ψ$_textrmtrunk$ with other continuous tree water status indicators such as the sap flow rate, the difference between canopy and air temperatures, or the variations of the trunk and fruit diameter, all the sensors were installed in 2022 in a commercial orchard of ‘Honeycrisp’ apple trees with M.9 rootstocks in Washinton State (USA). From the daily evolution of the Ψ$_textrmtrunk$, five indicators were considered: predawn, midday, minimum, daily mean, and daily range (the difference between the daily maximum and minimum values). The daily range of Ψ$_textrmtrunk$ was the most linked to the maximum daily shrinkage (MDS; R$^textrm2$ = 0.42), the canopy-to-air temperature (Tc-Ta; R$^textrm2$ = 0.32), and the sap flow rate (SF; R$^textrm2$ = 0.30). On the other hand, the relative fruit growth rate (FRGR) was more related to the minimum Ψ$_textrmtrunk$ (R$^textrm2$ = 0.33) and the daily mean Ψ$_textrmtrunk$ (R$^textrm2$ = 0.32) than to the daily range of Ψ$_textrmtrunk$. All indicators derived from Ψ$_textrmtrunk$ identified changes in tree water status after each irrigation event and had low coefficients of variation and high sensitivity. These results encourage Ψ$_textrmtrunk$ as a promising candidate for continuous monitoring of tree water status, however, more research is needed to better relate these measures with other widely studied plant-based indicators and identify good combinations of sensors and threshold values.\</p\>},

note = {Publisher: Frontiers},

keywords = {Continuous measurements, fruit growth, Plant-based sensors, Precision irrigation, Tree water status indicators, water potential},

pubstate = {published},

tppubtype = {article}

}

Close

Cookie	Duration	Description
cookielawinfo-checkbox-advertisement	1 year	Set by the GDPR Cookie Consent plugin, this cookie is used to record the user consent for the cookies in the "Advertisement" category .
cookielawinfo-checkbox-analytics	11 months	This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Analytics".
cookielawinfo-checkbox-functional	11 months	The cookie is set by GDPR cookie consent to record the user consent for the cookies in the category "Functional".
cookielawinfo-checkbox-necessary	11 months	This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary".
cookielawinfo-checkbox-others	11 months	This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Other.
cookielawinfo-checkbox-performance	11 months	This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Performance".
CookieLawInfoConsent	1 year	Records the default button state of the corresponding category & the status of CCPA. It works only in coordination with the primary cookie.
viewed_cookie_policy	11 months	The cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data.

Cookie	Duration	Description
_ga	2 years	The _ga cookie, installed by Google Analytics, calculates visitor, session and campaign data and also keeps track of site usage for the site's analytics report. The cookie stores information anonymously and assigns a randomly generated number to recognize unique visitors.
_ga_MBM6JBSF93	2 years	This cookie is installed by Google Analytics.

2024

Welcome to AgAID.org!