There are several elements to the ICME 2024 Technical Program. Submission instructions vary according to the program element. Please refer to the program-specific information applicable to you. General information pertaining to all program elements may be found after the program-specific information.
Regular and Special Session papers form the core of the ICME technical program.
If you would like to propose a Special Session, please see Call for Special Session Proposals for more information.
* Note that the contents of the supplemental material should be referred to appropriately in the paper and that reviewers are not obliged to look at it. All supplemental material must be zipped into a single file. There is a 20 MB limit on the size of this file.
Submissions should be made through https://cmt3.research.microsoft.com/ICMEW2024
If you would like to propose a Workshop, please see Call for Workshops for more information.
If you are submitting a paper to an approved Workshop, please see the appropriate Workshop site for more information. All Workshop papers will have the following commonalities:
If you are submitting an Industry/Application short paper, follow the instructions below. Further information about Industry/Application Short Papers can be found at Call for Industry/Application Papers
A Demo submission is a short (2-page) paper describing the demo. If the demo is accepted, this paper will be included in the USB Proceedings. Please see the Call for Demonstrations for further information.
If you would like to propose a Grand Challenge, please see Call for Grand Challenges for more information.
If you are submitting a contribution to an approved Grand Challenge, please see the appropriate Grand Challenge site for specific information. Most Grand Challenges will have the following commonalities:
All papers in the proceedings of the regular program and proceedings of the workshops, industry/application short papers, demo track, and grand challenges will be included in IEEE Xplore and indexed by EI Compendex.
The following links point to an example paper containing detailed formatting guidelines. They also constitute templates for Microsoft Word and LateX submissions.
We recommend that you use the Word file or LaTeX files to produce your document, since they have been set up to meet the formatting guidelines detailed in the example paper. When using these files, double-check the paper size in your page setup to make sure you are using the letter-size paper layout (8.5 inch X 11 inch). The LaTeX environment files specify suitable margins, page layout, text, and a bibliography style.
In particular, with LaTeX, there are cases where the top-margin of the resulting Postscript or PDF file does not meet the specified parameters. In this case, you may need to add a \topmargin=0mm command just after the \begin{document} command in your .tex file. The spacing of the top margin is not critical, as the page contents will be adjusted on the proceedings. The critical dimensions are the actual width and height of the page content.
When you have your document file ready, gather the following information before entering the submission system:
Important: ALL authors must be entered in the online form, and must appear in the online form in the same order in which the authors appear on the PDF.
EURL ECVAM promotes and facilitates the use of non-animal methods in testing and research.
EURL ECVAM is an integral part of the Joint Research Centre (JRC), the science and knowledge service of the European Commission. It is located in the JRC site in Ispra, Italy.
For over 30 years, the JRC has been working on the Three Rs – the Replacement, Reduction and Refinement of animal experiments. The mandate of EURL ECVAM is set out in the EU legislation on the protection of animals used for scientific purposes and includes a number of duties:
Our activities.
Find out about the validation process, validated test methods, how to submit a test method and much more.
Read our reviews on emerging non-animal models used for research in different disease areas.
Discover our education and training activities targeting secondary schools, universities and professional development.
Advancing alternative approaches through better knowledge sharing. Be part of the Three Rs knowledge community!
Making biological sense of COVID-19 using the Adverse Outcome Pathways (AOP) knowledge management framework.
We have an extensive experimental facility used for the development, validation and standardisation of in vitro methods.
The JRC-led initiative called PRO-MaP aims to improve methodological reporting and transparency in scientific publications to capitalise on innovation and improve health outcomes for all.
Among the 2023 highlights: new in vitro methods under consideration for regulatory application, a virtual reality application for education in schools, and enhancing collaboration to promote innovative non-animal approaches
To address current challenges in assessing and managing chemical risks, the JRC proposes a new innovative concept of “Chemicals 2.0” for future safety assessment and management.
Check out our FAQs to get a better understanding of who we are and what we do.
Our 'News from EURL ECVAM ' provides updates and highlights of our activities. Why not subscribe to receive it by email!
On the 25th of October 2022, the JRC launched a continuously open call for applications for the selection of members of the sub-groups operating under the ESAC.
JRC publication: Learning from the students - The impact of the JRC Summer School Non-animal Approaches in Science - Survey results
The 2023 EURL ECVAM Status Report outlines research and development activities, along with initiatives that foster the implementation and utilisation of non-animal methods and approaches in scientific research and regulation.
Via Enrico Fermi, 2749 21027 Ispra VA Italy
Share this page
Explore all metrics
In response to the increasingly complex problem of patrolling urban areas, the utilization of deep reinforcement learning algorithms for autonomous unmanned aerial vehicle (UAV) coverage path planning (CPP) has gradually become a research hotspot. CPP’s solution needs to consider several complex factors, including landing area, target area coverage and limited battery capacity. Consequently, based on incomplete environmental information, policy learned by sample inefficient deep reinforcement learning algorithms are prone to getting trapped in local optima. To enhance the quality of experience data, a novel reward is proposed to guide UAVs in efficiently traversing the target area under battery limitations. Subsequently, to improve the sample efficiency of deep reinforcement learning algorithms, this paper introduces a novel dynamic soft update method, incorporates the prioritized experience replay mechanism, and presents an improved deep double Q-network (IDDQN) algorithm. Finally, simulation experiments conducted on two different grid maps demonstrate that IDDQN outperforms DDQN significantly. Our method simultaneously enhances the algorithm’s sample efficiency and safety performance, thereby enabling UAVs to cover a larger number of target areas.
This is a preview of subscription content, log in via an institution to check access.
Subscribe and save.
Price includes VAT (Russian Federation)
Instant access to the full article PDF.
Rent this article via DeepDyve
Institutional subscriptions
V. G. Nair, R. S. Adarsh, K. Jayalakshmi, M. Dileep, and K. Guruprasad, “Cooperative online workspace allocation in the presence of obstacles for multi-robot simultaneous exploration and coverage path planning problem,” International Journal of Control, Automation, and Systems , vol. 21, no. 7, pp. 2338–2349, 2023.
Article Google Scholar
K. Kumar and N. Kumar, “Region coverage-aware path planning for unmanned aerial vehicles: A systematic review,” Physical Communication , vol. 59, 102073, 2023.
A. Janchiv, D. Batsaikhan, B. Kim, W. G. Lee, and S.-G. Lee, “Time-efficient and complete coverage path planning based on flow networks for multi-robots,” International Journal of Control, Automation, and Systems , vol. 11, no. 2, pp. 369–376, 2013.
H. Ucgun, I. Okten, U. Yuzgec, and M. Kesler, “Test platform and graphical user interface design for vertical takeoff and landing drones,” Romanian Journal of Information Science and Technology , vol. 25, no. 3–4, pp. 350–367, 2022.
Google Scholar
C. Hu, Z. Meng, G. Qu, H.-S. Shin, and A. Tsourdos, “Distributed cooperative path planning for tracking ground moving target by multiple fixed-wing UAVs via DMPC-GVD in urban environment,” International Journal of Control, Automation, and Systems , vol. 19, no. 2, pp. 823–836, 2021.
J. Ni, Y. Chen, G. Tang, J. Shi, W. Cao, and P. Shi, “Deep learning-based scene understanding forautonomous robots: A survey,” Intelligence & Robotics , vol. 3, no. 3, pp. 374–401, 2023.
E. M. Arkin, S. P. Fekete, and J. S. Mitchell, “Approximation algorithms for lawn mowing and milling,” Computational Geometry: Theory and Applications , vol. 17, no. 1–2, pp. 25–50, 2000.
Article MathSciNet Google Scholar
J. Xie, L. R. G. Carrillo, and L. Jin, “An integrated traveling salesman and coverage path planning problem for unmanned aircraft systems,” IEEE Control Systems Letters , vol. 3, no. 1, pp. 67–72, 2019.
C. Carr and P. Wang, “Fast-spanning ant colony optimisation (FaSACO) for mobile robot coverage path planning,” arXiv preprint arXiv:2205.15691 , 2022.
J. Ni, L. Yang, L. Wu, and X. Fan, “An improved spinal neural system-based approach forheterogeneous AUVs cooperative hunting,” International Journal of Fuzzy Systems , vol. 20, no. 2, pp. 672–686, 2018.
H. Choset, “Coverage of known spaces: The boustrophedon cellular decomposition,” Autonomous Robots , vol. 9, no. 3, pp. 247–253, 2000.
R. Mannadiar and I. Rekleitis, “Optimal coverage of a known arbitrary environment,” Proc. of IEEE International Conference on Robotics and Automation , pp. 5525–5530, 2010.
J. Ni, K. Shen, Y. Chen, and S. X. Yang, “An improved SSD-like deep network-based object detection method for indoor scenes,” IEEE Transactions on Instrumentation and Measurement , vol. 72, pp. 1–15, 2023.
X. Song, N. Wu, S. Song, and V. Stojanovic, “Switchinglike event-triggered state estimation for reaction-diffusion neural networks against DoS attacks,” Neural Processing Letters , vol. 55, no. 7, pp. 8997–9018, 2023.
J. Ni, Z. Zhang, K. Shen, G. Tang, and S. X. Yang, “An improved deep network-based RGB-D semantic segmentation method for indoor scenes,” International Journal of Machine Learning and Cybernetics , vol. 15, no. 2, pp. 589–604, 2024.
Y. Chen, J. Ni, G. Tang, W. Cao, and S. X. Yang, “An improved dense-to-sparse cross-modal fusion network for 3D object detection in RGB-D images,” Multimedia Tools and Applications , vol. 83, no. 4, pp. 12159–12184, 2024.
W. Li, M. Yue, J. Shangguan, and Y. Jin, “Navigation of mobile robots based on deep reinforcement learning: Reward function optimization and knowledge transfer,” International Journal of Control, Automation, and Systems , vol. 21, no. 2, pp. 563–574, 2023.
P.-A. Andersen, M. Goodwin, and O.-C. Granmo, “Deep RTS: A game environment for deep reinforcement learning in real-time strategy games,” Proc. of IEEE Conference on Computational Intelligence and Games (CIG) , pp. 1–8, 2018.
C.-H. Min and J.-B. Song, “Hierarchical end-to-end control policy for multi-degree-of-freedom manipulators,” International Journal of Control, Automation, and Systems , vol. 20, no. 10, pp. 3296–3311, 2022.
G. Chen, Y. Lu, X. Yang, and H. Hu, “Reinforcement learning control for the swimming motions of a beaverlike, single-legged robot based on biological inspiration,” Robotics and Autonomous Systems , vol. 154, 104116, 2022.
W. Zang, P. Yao, K. Lv, and D. Song, “A deep Q network assisted method for underwater gliders standoff tracking to the static target,” Neural Computing and Applications , vol. 34, no. 23, pp. 20575–20587, 2022.
I. A. Zamfirache, R.-E. Precup, R.-C. Roman, and E. M. Petriu, “Neural network-based control using actor-critic reinforcement learning and grey wolf optimizer with experimental servo system validation,” Expert Systems with Applications , vol. 225, 120112, 2023.
J. Chen, R. Ma, and J. Oyekan, “A deep multi-agent reinforcement learning framework for autonomous aerial navigation to grasping points on loads,” Robotics and Autonomous Systems , vol. 167, 104489, 2023.
V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski, S. Petersen, C. Beattie, A. Sadik, I. Antonoglou, H. King, D. Kumaran, D. Wierstra, S. Legg, and D. Hassabis, “Human-level control through deep reinforcement learning,” Nature , vol. 518, no. 7540, pp. 529–533, 2015.
W. Choi, H. Kang, and J. Lee, “Robust Localization of Unmanned Surface Vehicle Using DDQN-AM,” International Journal of Control, Automation, and Systems , vol. 19, no. 5, pp. 1920–1930, 2021.
Z. Shen, P. Agrawal, J. P. Wilson, R. Harvey, and S. Gupta, “CPPNet: A coverage path planning network,” Proc. of OCEANS 2021: San Diego–Porto , pp. 1–5, 2021.
J. Hu, H. Niu, J. Carrasco, B. Lennox, and F. Arvin, “Voronoi-based multi-robot autonomous exploration in unknown environments via deep reinforcement learning,” IEEE Transactions on Vehicular Technology , vol. 69, no. 12, pp. 14413–14423, 2020.
M. Theile, H. Bayerlein, R. Nai, D. Gesbert, and M. Caccamo, “UAV coverage path planning under varying power constraints using deep reinforcement learning,” Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , pp. 1444–1449, 2020.
M. Theile, H. Bayerlein, R. Nai, D. Gesbert, and M. Caccamo, “UAV path planning using global and local map information with deep reinforcement learning,” Proc. of 20th International Conference on Advanced Robotics (ICAR) , pp. 539–546, 2021.
S. Dogru and L. Marques, “ECO-CPP: Energy constrained online coverage path planning,” Robotics and Autonomous Systems , vol. 157, 104242, 2022.
L. P. Kaelbling, M. L. Littman, and A. R. Cassandra, “Planning and acting in partially observable stochastic domains,” Artificial Intelligence , vol. 101, no. 1–2, pp. 99–134, 1998.
T. Hester, T. Schaul, A. Sendonaris, M. Vecerik, B. Piot, I. Osband, O. Pietquin, D. Horgan, G. Dulac-Arnold, M. Lanctot, J. Quan, J. Agapiou, J. Z. Leibo, and A. Gruslys, “Deep q-learning from demonstrations,” Proc. of the AAAI Conference on Artificial Intelligence , vol. 32, no. 1, pp. 3223–3230, 2018.
H. Van Hasselt, A. Guez, and D. Silver, “Deep reinforcement learning with double q-learning,” Proc. of the AAAI Conference on Artificial Intelligence , vol. 30, no. 1, pp. 2094–2100, 2016.
H. Jiang, D. Shi, C. Xue, Y. Wang, G. Wang, and Y. Zhang, “Friend-or-foe deep deterministic policy gradient,” Proc. of IEEE International Conference on Systems, Man, and Cybernetics (SMC) , pp. 3523–2530, 2020.
Y. Gu, Y. Cheng, C. P. Chen, and X. Wang, “Proximal policy optimization with policy feedback,” IEEE Transactions on Systems, Man, and Cybernetics: Systems , vol. 52, no. 7, pp. 4600–4610, 2021.
P. Li, Y. Wang, and Z. Gao, “Path planning of mobile robot based on improved TD3 algorithm,” Proc. of IEEE International Conference on Mechatronics and Automation (ICMA) , pp. 715–720, 2022.
T. Kobayashi and W. E. L. Ilboudo, “T-soft update of target network for deep reinforcement learning,” Neural Networks , vol. 136, pp. 63–71, 2021.
T. Schaul, J. Quan, I. Antonoglou, and D. Silver, “Prioritized experience replay,” arXiv preprint arXiv:1511.05952 ,2015.
J. Ni, K. Shen, Y. Chen, W. Cao, and S. X. Yang, “An improved deep network-based scene classification method for self-driving cars,” IEEE Transactions on Instrumentation and Measurement , vol. 71, pp. 1–14, 2022.
H. Bayerlein, M. Theile, M. Caccamo, and D. Gesbert, “UAV path planning for wireless data harvesting: A deep reinforcement learning approach,” Proc. of GLOBECOM 2020–2020 IEEE Global Communications Conference , pp. 1–6, 2020.
J. P. G. Carvalho and A. P. Aguiar, “A reinforcement learning based online coverage path planning algorithm,” Proc. of IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC) , pp. 81–86, 2023.
Z. Zhang, X. Song, X. Sun, and V. Stojanovic, “Hybrid-driven-based fuzzy secure filtering for nonlinear parabolic partial differential equation systems with cyber attacks,” International Journal of Adaptive Control and Signal Processing , vol. 37, no. 2, pp. 380–398, 2023.
H. Tao, J. Li, Y. Chen, V. Stojanovic, and H. Yang, “Robust point-to-point iterative learning control with trial-varying initial conditions,” IET Control Theory and Applications , vol. 14, no. 19, pp. 3344–3350, 2020.
Download references
Authors and affiliations.
College of Artificial Intelligence and Automation, Hohai University, Changzhou, Jiangsu, 213200, China
Jianjun Ni, Yu Gu, Yang Gu, Yonghao Zhao & Pengfei Shi
College of Information Science and Engineering, Hohai University, Changzhou, Jiangsu, 213200, China
Jianjun Ni & Pengfei Shi
You can also search for this author in PubMed Google Scholar
Correspondence to Jianjun Ni or Yang Gu .
The authors declare that there is no competing financial interest or personal relationship that could have appeared to influence the work reported in this paper.
Publisher’s Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was supported by National Natural Science Foundation of China (61873086), and the National Key R&D Program of China (2022YFB4703402).
Jianjun Ni received his Ph.D. degree from the School of Information and Electrical Engineering from China University of Mining and Technology, Xuzhou, China, in 2005. Currently he is a Professor of College of Artificial Intelligence and Automation, Hohai University, China. He was a Visiting Professor with the Advanced Robotics & Intelligent Systems (ARIS) Laboratory at the University of Guelph in Canada from November 2009 to October 2010. He has published over 100 papers in related international conferences and journals. He serves as an Associate Editor and reviewer of a number of international journals. His research interests include control systems, neural networks, robotics, machine intelligence and multi-agent system.
Yu Gu received his B.S. degree from Hohai University, China, in 2021. Currently, he is working toward an M.S. degree in detection technology and automation devices systems, College of Artificial Intelligence and Automation at Hohai University. His research interests include deep reinforcement learning and coverage path planning.
Yang Gu received his Ph.D. degree in electrical engineering and automation from the China University of Mining and Technology in 2022. He is currently a lecture in the College of Artificial Intelligence and Automation, Hohai University. His research interest includes reinforcement learning.
Yonghao Zhao received his master’s degree from Nanjing Tech University, China, in 2022. Currently, he is working towards a Ph.D. degree in artificial intelligence, College of Artificial Intelligence and Automation, Hohai University. His research interests include machine learning, robot control, and so on.
Pengfei Shi received his B.S. degree from Nanjing University of Information Science and Technology, Nanjing, China, his M.S. and Ph.D. degrees from Hohai University, Nanjing, China, in 2011 and 2016, respectively. He now works in the College of Artificial Intelligence and Automation, Hohai University, Changzhou, China. His research interests include machine learning, machine vision, and underwater detection.
Reprints and permissions
Ni, J., Gu, Y., Gu, Y. et al. UAV Coverage Path Planning With Limited Battery Energy Based on Improved Deep Double Q-network. Int. J. Control Autom. Syst. 22 , 2591–2601 (2024). https://doi.org/10.1007/s12555-023-0724-9
Download citation
Received : 28 October 2023
Revised : 26 January 2024
Accepted : 15 February 2024
Published : 02 August 2024
Issue Date : August 2024
DOI : https://doi.org/10.1007/s12555-023-0724-9
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative
Get help with your research
Join ResearchGate to ask questions, get input, and advance your work.
IMAGES
VIDEO
COMMENTS
4. Track your paper. 5. Share and promote. 1. Find a journal. Find out the journals that could be best suited for publishing your research. For a comprehensive list of Elsevier journals check our Journal Catalog. You can also match your manuscript using the JournalFinder tool, then learn more about each journal.
All submissions must be pre-formated to meet the HIR style guide. Submissions must also include images, captions, and sourcing as per the style guide. Failure to follow these guidelines will result in your submission being archived without response. Please be aware that a small fraction of submissions are chosen for publication.
3. Submit and revise. You can submit to most Elsevier journals using our online systems. The system you use will depend on the journal to which you submit. You can access the relevant submission system via the "submit your paper" link on the Elsevier.com journal homepage of your chosen journal. Alternatively, if you have been invited to submit ...
Read more. - Electronic submission. - Reviewing and acceptance. - Managing copyright - The "MyPublication" process. - Copy editing and language polishing. - Data processing and type setting. - Article Tracking. - Checking your article: proofing procedure. - e.Proofing - Makes editing easy!
Submitting your paper. The Instructions for Contributors document for each journal will explain the process for submitting your paper to that particular title, including guidance on additional information you should include alongside your manuscript. A growing proportion of our journals now use an online submission system - in most cases ...
3. Submit your article according to the journal's submission guidelines. Go to the "author's guide" (or similar) on the journal's website to review its submission requirements. Once you are satisfied that your paper meets all of the guidelines, submit the paper through the appropriate channels.
Step 1: Choosing a journal. Choosing which journal to publish your research paper in is one of the most significant decisions you have to make as a researcher. Where you decide to submit your work can make a big difference to the reach and impact your research has. It's important to take your time to consider your options carefully and ...
Once you think your manuscript is ready for submission, the next important step is to read the aims and scope of the journals in your target research area. Doing so will improve the chances of having your manuscript accepted for publishing. Submit a cover letter with the manuscript. Never underestimate the importance of a cover letter addressed ...
The introduction section should be approximately three to five paragraphs in length. Look at examples from your target journal to decide the appropriate length. This section should include the elements shown in Fig. 1. Begin with a general context, narrowing to the specific focus of the paper.
Select ' Submit your article ' on the homepage of the journal you would like to publish in. This option may not always be available as some journals do not accept submissions. Sign in to Editorial Manager, or register if you are a first-time user. Follow the steps to submit your article. After submitting your article, use the reference number ...
Ensure that your submission package is complete. Understand the submission process/system used for publishing in an international journal and find out whom to contact and how in case you have queries. Write a compelling cover letter. This document is probably the first submission item that a journal editor will read and can influence the fate ...
Originality: The paper must contain original and unpublished work.; File Format: Papers should be submitted as Microsoft Word files (*.doc) or as Rich Text Format files (*.rtf).; Length: Maximum words of possible submission categories: - Traditional Essays (4000) - Original Data-Centered Research (2000, free of all technical jargon) - Case Studies (2000)
The introduction section should be approximately three to five paragraphs in length. Look at examples from your target journal to decide the appropriate length. This section should include the elements shown in Fig. 1. Begin with a general context, narrowing to the specific focus of the paper.
Make some points of your findings and note them down. Choose the journal in which you want to publish the paper. Check the sample paper and "Instruction to Authors" or "Author's Guide" of that particular journal. Prepare your manuscript according to the format.
Once you are done with the above mentioned steps, then you are eligible for writing a paper. 2. Read existing Papers. Read everything that might be relevant gives you different perspective of the focus topic. But be selective too, for not getting to much deviated from you topic of interest.
The research paper publication process starts with the submission of your research paper via online submission. Authors can submit original research papers, case studies, survey paper, exntended versions of previously published papers in international journals & conferences. The peer review process usually complete within 09-12 days time ...
Knowledge and Information Systems is an international forum publishing state-of-the-art research on emerging topics in knowledge and advanced information systems. Examines theoretical foundations, infrastructure, and enabling technologies of knowledge and information systems. Each individual issue focuses on a small number of theme areas.
Industry/Application Papers. If you are submitting an Industry/Application short paper, follow the instructions below. Further information about Industry/Application Short Papers can be found at Call for Industry/Application Papers. Submission deadline; Length: Papers must be no longer than 4 pages, including all text, figures, and references.
For over 30 years, the JRC has been working on the Three Rs - the Replacement, Reduction and Refinement of animal experiments. The mandate of EURL ECVAM is set out in the EU legislation on the protection of animals used for scientific purposes and includes a number of duties:. Research and development, supported through collaboration with EU and international research initiatives
Use our pre-submission checklist. Avoid common mistakes on your manuscript. References. V. G. Nair, ... He has published over 100 papers in related international conferences and journals. He serves as an Associate Editor and reviewer of a number of international journals. His research interests include control systems, neural networks, robotics ...
All accepted papers will be published by SPIE - The International Society for Optical Engineering (ISSN: 0277-786X), and submitted to EI Compendex, Scopus for indexing. Important Dates: Full Paper ...
FSU assistant professor Julie Sheffler teaches in the university's College of Medicine, and presented a paper at this week's conference. Her paper showcased research on nutrition education and ...
The 6th ACM/IEEE International Conference on Automation of Software Test (AST 2025) Software pervasiveness in both industry and digital society, as well as the proliferation of Artificial Intelligence (AI) technologies are continuously leading to emerging needs from both software producers and consumers. Infrastructures, software components, and applications aim to hide their increasing ...
Research Paper On Niagara Falls; ... There is an international boundary between the United States and Canada. The birth of Niagara Falls can be traced back more than 12,000 years to the end of the last glacial period. During periods of peak flow in the summer and fall, more than 700,000 gallons of water per second pour over Niagara Falls; and ...