| 1. |
- Li, Peiran, et al.
(författare)
-
Understanding rooftop PV panel semantic segmentation of satellite and aerial images for better using machine learning
- 2021
-
Ingår i: Advances in Applied Energy. - : Elsevier BV. - 2666-7924. ; 4, s. 100057-100057
-
Tidskriftsartikel (refereegranskat)abstract
- The photovoltaic (PV) industry boom and increased PV applications call for better planning based on accurate and updated data on the installed capacity. Compared with the manual statistical approach, which is often time-consuming and labor-intensive, using satellite/aerial images to estimate the existing PV installed capacity offers a new method with cost-effective and data-consistent features. Previous studies investigated the feasibility of segmenting PV panels from images involving machine learning technologies. However, due to the particular characteristics of PV panel semantic-segmentation, the machine learning tools need to be designed and applied with careful considerations of the issue formulation, data quality, and model explainability. This paper investigated the characteristics of PV panel semantic-segmentation from the perspective of computer vision. The results reveal that the PV panel image data has several specific characteristics: highly class-imbalance and non-concentrated distribution; homogeneous texture and heterogenous color features; and the notable resolution threshold for effective semantic-segmentation. Moreover, this paper provided recommendations for data obtaining and model design, aiming at each observed character from the viewpoints of recent solutions in computer vision, which can be helpful for future improvement of the PV panel semantic-segmentation.
|
|
| 2. |
- Li, Wenjing, et al.
(författare)
-
PredLife : Predicting Fine-Grained Future Activity Patterns
- 2023
-
Ingår i: IEEE Transactions on Big Data. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 2332-7790. ; 9:6, s. 1658-1669
-
Tidskriftsartikel (refereegranskat)abstract
- Activity pattern prediction is a critical part of urban computing, urban planning, intelligent transportation, and so on. Based on a dataset with more than 10 million GPS trajectory records collected by mobile sensors, this research proposed a CNN-BiLSTM-VAE-ATT-based encoder-decoder model for fine-grained individual activity sequence prediction. The model combines the long-term and short-term dependencies crosswise and also considers randomness, diversity, and uncertainty of individual activity patterns. The proposed results show higher accuracy compared to the ten baselines. The model can generate high diversity results while approximating the original activity patterns distribution. Moreover, the model also has interpretability in revealing the time dependency importance of the activity pattern prediction.
|
|
| 3. |
- Shi, Xiaodan, et al.
(författare)
-
MetaTraj : Meta-Learning for Cross-Scene Cross-Object Trajectory Prediction
- 2023
-
Ingår i: IEEE transactions on intelligent transportation systems (Print). - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 1524-9050 .- 1558-0016.
-
Tidskriftsartikel (refereegranskat)abstract
- Long-term pedestrian trajectory prediction in crowds is highly valuable for safety driving and social robot navigation. The recent research of trajectory prediction usually focuses on solving the problems of modeling social interactions, physical constraints and multi-modality of futures without considering the generalization of prediction models to other scenes and objects, which is critical for real-world applications. In this paper, we propose a general framework that makes trajectory prediction models able to transfer well across unseen scenes and objects by quickly learning the prior information of trajectories. The trajectory sequences are closely related to the circumstance setting (e.g. exits, roads, buildings, entries etc.) and the objects (e.g. pedestrians, bicycles, vehicles etc.). We argue that those trajectory information varying across scenes and objects makes a trained prediction model not perform well over unseen target data. To address it, we introduce MetaTraj that contains carefully designed sub-tasks and meta-tasks to learn prior information of trajectories related to scenes and objects, which then contributes to accurate long-term future prediction. Both sub-tasks and meta-tasks are generated from trajectory sequences effortlessly and can be easily integrated into many prediction models. Extensive experiments over several trajectory prediction benchmarks demonstrate that MetaTraj can be applied to multiple prediction models and enables them generalize well to unseen scenes and objects.
|
|
| 4. |
- Zhang, Haoran, et al.
(författare)
-
1.6 Million transactions replicate distributed PV market slowdown by COVID-19 lockdown
- 2021
-
Ingår i: Applied Energy. - : ELSEVIER SCI LTD. - 0306-2619 .- 1872-9118. ; 283
-
Tidskriftsartikel (refereegranskat)abstract
- Solar PV has seen a spectacular market development in recent years and has become a cost competitive source of electricity in many parts of the world. Yet, prospective observations show that the coronavirus pandemic could impact renewable energy projects, especially in the distributed market. Tracking and attributing the economic footprint of COVID-19 lockdowns in the photovoltaic sector poses a significant research challenge. Based on millions of financial transaction records and 44 thousand photovoltaic installation records, we tracked the spatiotemporal sale network of the distributed photovoltaic market and explored the extent of market slowdown. We found that a two-month lockdown duration can be assessed as a high-risk threshold value. When the lockdown duration exceeds the threshold value, the monthly value-added loss reaches 67.7%, and emission reduction capacity is cut by 64.2% over the whole year. We show that risks of a slowdown in PV deployment due to COVID19 lockdowns can be mitigated by comprehensive incentive strategies for the distributed PV market amid market uncertainties.
|
|
| 5. |
- Zhang, Haoran, et al.
(författare)
-
Epidemic versus economic performances of the COVID-19 lockdown : A big data driven analysis
- 2022
-
Ingår i: Cities. - : Elsevier BV. - 0264-2751 .- 1873-6084. ; 120
-
Tidskriftsartikel (refereegranskat)abstract
- Lockdown measures have been a “panacea” for pandemic control but also a violent “poison” for economies.Lockdown policies strongly restrict human mobility but mobility reduce does harm to economics. Governmentsmeet a thorny problem in balancing the pros and cons of lockdown policies, but lack comprehensive andquantified guides. Based on millions of financial transaction records, and billions of mobility data, we trackedspatio-temporal business networks and human daily mobility, then proposed a high-resolution two-sidedframework to assess the epidemiological performance and economic damage of different lockdown policies. Wefound that the pandemic duration under the strictest lockdown is less about two months than that under thelightest lockdown, which makes the strictest lockdown characterize both epidemiologically and economicallyefficient. Moreover, based on the two-sided model, we explored the spatial lockdown strategy. We argue thatcutting off intercity commuting is significant in both epidemiological and economical aspects, and finally helpedgovernments figure out the Pareto optimal solution set of lockdown strategy.
|
|
| 6. |
- Zhang, Haoran, et al.
(författare)
-
Urban power load profiles under ageing transition integrated with future EVs charging
- 2021
-
Ingår i: Advances in Applied Energy. - : Elsevier BV. - 2666-7924. ; 1, s. 100007-100007
-
Tidskriftsartikel (refereegranskat)abstract
- Understanding ageing transition caused fine-grained changes of electricity profile is the significant insight for coping with future threatens in grid flexibility management. The research gaps for the hourly-basis knowledge exist due to challenges in microanalysis on user-side behavior. Based on billions of users’ behavior data, we investigated the changes on the load profiles due to population aging. We found that owing to ageing transition, the participation population in high electricity-density activities decreases by about 8%. The corresponding shift in driving behavior rises the 14% difference between peak charging load and valley. We concluded that population aging will dramatically change both the magnitude and shape of future dynamic-load profiles. Therefore, we further suggested a new solution with comprehensive and quantitative management for PVs development and the smart charging market with smooth operation of the grid in coupling the potential challenges caused by the ageing issue.
|
|
