Spatial-Temporal Multi-Task Learning for Within-Field Cotton Yield Prediction

Nguyen, Long; Zhu, Jiazhen; Lin, Zhe; Du, Hanxiang; Yang, Zhou; Guo, Wenxuan

doi:10.1007/978-3-030-16148-4_27

Cited by 21 publications

(19 citation statements)

References 26 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the current study, the use of publicly available datasets to predict lint yield across two field sites provided poorer predictions at squaring (RMSE = 0.21-26 t ha −1 , LCCC = 0.25-0.32) compared with later in the season at flowering (RMSE = 0.17 t ha −1 , LCCC = 0.50-0.66) and boll-fill (RMSE = 0.15-0.20 t ha −1 , LCCC = 0.55-0.62). These findings are in agreement with other studies where the addition of more data improved yield predictions as the season progressed (Filippi, Jones, et al, 2019;Filippi et al, 2020;Huang et al, 2013;Nguyen et al, 2019;Thomasson et al, 2004). The improved predictions in the current study later in the season were primarily attributed to stronger relationships between GNDVI and yield.…”

Section: Model Performancesupporting

confidence: 92%

Predicting within‐field cotton yields using publicly available datasets and machine learning

2021

View full text Add to dashboard Cite

Early detection of within-field yield variability for high-value commodity crops, such as cotton (Gossypium spp.), offers growers potential to improve decision-making, optimize yields, and increase profits. Over recent years, publicly available datasets have become increasingly available and at a resolution where within-field yield prediction is possible. However, the viability of using these datasets with machine learning to predict within-field cotton lint yield at key growth stages are largely unknown. This study was conducted on two cotton fields, located near Mungindi, New South Wales, Australia. Three years of yield data, soil, elevation, rainfall, and Landsat imagery were collected from each field. A total of 12 models were created using: (a) two machine learning algorithms: random forest (RF) and gradient boosting machines (GBM); (b) three growth stages: squaring, flowering, and boll-fill; and(c) two different amounts of variables: all variables and the optimal variables determined by a recursive feature elimination (RFE). Results showed a strong agreement between predicted and observed yields at flowering and boll-fill when more information was available. At flowering and boll-fill, root mean square error (RMSE) ranged between 0.15 and 0.20 t ha −1 and Lin's concordance correlation coefficient (LCCC) ranged between 0.50 and 0.66, with RF providing superior results in most cases. Models created using the optimal variables determined by the RFE provided similar results compared to using all variables, allowing greater model accuracy and resolution with targeted sampling. Overall, these findings indicate significant potential of publicly available datasets to predict within-field cotton yield and guide decisionmaking in-season.

show abstract

Section: Model Performancesupporting

confidence: 92%

Predicting within‐field cotton yields using publicly available datasets and machine learning

2021

View full text Add to dashboard Cite

show abstract

“…To capture the real-time dynamics of input, Addict Free utilizes a LSTM model for relapse time series prediction due to its wellhandling ability of long and short term time dependency. The model is also utilized in other types of prediction as in [4] and [1][2][3]. Figure 5 shows the basic structure of LSTM.…”

Section: Methods 41 Relapse Predictionmentioning

confidence: 99%

Addict Free - A Smart and Connected Relapse Intervention Mobile App

Yang

Reddy

Kesidi

2019

Proceedings of the 16th International Symposium on Spatial and Temporal Databases

Self Cite

View full text Add to dashboard Cite

It is widely acknowledged that addiction relapse is highly associated with spatial-temporal factors such as some specific places or time periods. Current studies suggest that those factors can be utilized for better relapse interventions, however, there is no relapse prevention application that makes use of those factors. In this paper, we introduce a mobile app called "Addict Free", which records user profiles, tracks relapse history and summarizes recovering statistics to help users better understand their recovering situations. Also, this app builds a relapse recovering community, which allows users to ask for advice and encouragement, and share relapse prevention experience. Moreover, machine learning algorithms that ingest spatial and temporal factors are utilized to predict relapse, based on which helpful addiction diversion activities are recommended by a recovering recommendation algorithm. By interacting with users, this app targets at providing smart suggestions that aim to stop relapse, especially for alcohol and tobacco addiction users. CCS CONCEPTS• Applied computing → Health care information systems.

show abstract

“…More broadly speaking, the issues of merging multi-site data have been actively investigated in recent literature on medical image analysis. For instance, Nguyen et al [25] proposed a novel multi-site learning algorithm to learn different features and aggregate spatial-temporal features through a weighted regularizer based on an integrated multiple heterogeneous dataset. The deep multi-task learning (MTL) framework [26] could effectively improve the accuracy of skin lesion classification through the additional context information provided by body location.…”

Section: Related Workmentioning

confidence: 99%

Contrastive Cross-Site Learning With Redesigned Net for COVID-19 CT Classification

Wang

Liu

Dou

2020

IEEE J. Biomed. Health Inform.

170

142

View full text Add to dashboard Cite

The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries. With the continuous growth of new infections, developing automated tools for COVID-19 identification with CT image is highly desired to assist the clinical diagnosis and reduce the tedious workload of image interpretation. To enlarge the datasets for developing machine learning methods, it is essentially helpful to aggregate the cases from different medical systems for learning robust and generalizable models. This paper proposes a novel joint learning framework to perform accurate COVID-19 identification by effectively learning with heterogeneous datasets with distribution discrepancy. We build a powerful backbone by redesigning the recently proposed COVID-Net in aspects of network architecture and learning strategy to improve the prediction accuracy and learning efficiency. On top of our improved backbone, we further explicitly tackle the cross-site domain shift by conducting separate feature normalization in latent space. Moreover, we propose to use a contrastive training objective to enhance the domain invariance of semantic embeddings for boosting the classification performance on each dataset. We develop and evaluate our method with two public large-scale COVID-19 diagnosis datasets made up of CT images. Extensive experiments show that our approach consistently improves the performanceson both datasets, outperforming the original COVID-Net trained on each dataset by 12.16% and 14.23% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.

show abstract

Spatial-Temporal Multi-Task Learning for Within-Field Cotton Yield Prediction

Cited by 21 publications

References 26 publications

Predicting within‐field cotton yields using publicly available datasets and machine learning

Predicting within‐field cotton yields using publicly available datasets and machine learning

Addict Free - A Smart and Connected Relapse Intervention Mobile App

Contrastive Cross-Site Learning With Redesigned Net for COVID-19 CT Classification

Contact Info

Product

Resources

About