DRLIC: Deep Reinforcement Learning for Irrigation Control

Ding, Xianzhong; Du, Wan

doi:10.1109/ipsn54338.2022.00011

Cited by 13 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using both surface and subsurface drip irrigation methods and perlite application in both half and full amount, water savings of approximately 50% were achieved. These findings agree with [3], [4], and [5], as well as [2].…”

Section: Effect Of Drip Irrigation Methods and Perlite Application On...supporting

confidence: 92%

“…[3] highlighted that irrigation scheduling is a water management strategy aimed to efficiently adding and not wasting water. [4] emphasized the importance of irrigation scheduling for maximizing water use efficiency and avoiding excessive water application that can negatively impact both soil and plants. [5] found that the total water consumption for potato crop during its growth period (96-day) was about 238.85 mm per season at a 50% depletion rate under surface drip irrigation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effect of Drip Irrigation Manners and Perlite Application on Water Consumption and Water Use Efficiency for Potato Crop

Al-Obaidi,

Al-Mehmdy

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

A field study was conducted at the Agricultural Research Station affiliated to the College of Agriculture, located in Al-Buetha area, Al-Ramadi district, central Anbar province, Iraq. (33°26′40" N latitude and 48°10′43" E longitude). The study was carried out during the autumn season in 2022 in a sedimentary soil with a sandy clay loam texture. The study aimed to investigate the role of surface and subsurface drip irrigation methods, along with the perlite addition, in terms of water consumption and water use efficiency for potato crop. The study included two main factors. The first factor was the irrigation system, which consisted of two methods: surface drip irrigation (SD) and subsurface drip irrigation (SSD). The second factor was the perlite application, which had three levels: without perlite (control treatment, P0), addition of half the calculated amount of perlite at a depth of 0.20m from the soil surface (Ph), and addition the full calculated amount of perlite at the same depth (Pf). The experimental design used was a randomized complete block design (RCBD). potato tubers (variety of EL BEIDA) were planted on September 27, 2022. Irrigation was scheduled when 50% of the available water was depleted, based on evaporation pan Class A. The results of the study showed that the best water consumption value for the potato crop was achieved under subsurface drip irrigation with the addition of both full and half amounts of perlite, with a value of 290.40 mm per season. Subsurface drip irrigation method significantly superior to surface drip irrigation in terms of water use efficiency, especially when full and half amounts of perlite were added, with values of 252.28 and 218.70 kg m-3, respectively.

show abstract

Section: Effect Of Drip Irrigation Methods and Perlite Application On...supporting

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Effect of Drip Irrigation Manners and Perlite Application on Water Consumption and Water Use Efficiency for Potato Crop

Al-Obaidi,

Al-Mehmdy

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Deep learning has found application across various domains and has been utilized in a multitude of applications, including code generation [30,32], building control [21,22], irrigation scheduling [19,20], and even in tasks related to epistemic uncertainty and occupancy estimation [6,41]. These applications showcase the versatility and adaptability of deep learning techniques.…”

Section: Introductionmentioning

confidence: 99%

HPC-GPT: Integrating Large Language Model for High-Performance Computing

Ding,

Chen,

Emani

et al. 2023

Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analys

Self Cite

View full text Add to dashboard Cite

Large Language Models (LLMs), including the LLaMA model, have exhibited their efficacy across various general-domain natural language processing (NLP) tasks. However, their performance in highperformance computing (HPC) domain tasks has been less than optimal due to the specialized expertise required to interpret the model's responses. In response to this challenge, we propose HPC-GPT, a novel LLaMA-based model that has been supervised finetuning using generated QA (Question-Answer) instances for the HPC domain. To evaluate its effectiveness, we concentrate on two HPC tasks: managing AI models and datasets for HPC, and data race detection. By employing HPC-GPT, we demonstrate comparable performance with existing methods on both tasks, exemplifying its excellence in HPC-related scenarios. Our experiments on open-source benchmarks yield extensive results, underscoring HPC-GPT's potential to bridge the performance gap between LLMs and HPC-specific tasks. With HPC-GPT, we aim to pave the way for LLMs to excel in HPC domains, simplifying the utilization of language models in complex computing applications.

show abstract

“…For this reason, some studies [18,19] have little practical relevance because they use learning environments whose dynamics are empirical models directly estimated using historical observations. Importantly, to "discover" good decision rules, RL agents need to stumble across unseen states presented by environmental extrapolation, which is empirical models are known to be poor at.…”

Section: Introductionmentioning

confidence: 99%

Deep reinforcement learning for irrigation scheduling using high-dimensional sensor feedback

Saikai,

Peake,

Chenu

2023

PLOS Water

View full text Add to dashboard Cite

Deep reinforcement learning has considerable potential to improve irrigation scheduling in many cropping systems by applying adaptive amounts of water based on various measurements over time. The goal is to discover an intelligent decision rule that processes information available to growers and prescribes sensible irrigation amounts for the time steps considered. Due to the technical novelty, however, the research on the technique remains sparse and impractical. To accelerate the progress, the paper proposes a principled framework and actionable procedure that allow researchers to formulate their own optimisation problems and implement solution algorithms based on deep reinforcement learning. The effectiveness of the framework was demonstrated using a case study of irrigated wheat grown in a productive region of Australia where profits were maximised. Specifically, the decision rule takes nine state variable inputs: crop phenological stage, leaf area index, extractable soil water for each of the five top layers, cumulative rainfall and cumulative irrigation. It returns a probabilistic prescription over five candidate irrigation amounts (0, 10, 20, 30 and 40 mm) every day. The production system was simulated at Goondiwindi using the APSIM-Wheat crop model. After training in the learning environment using 1981–2010 weather data, the learned decision rule was tested individually for each year of 2011–2020. The results were compared against the benchmark profits obtained by a conventional rule common in the region. The discovered decision rule prescribed daily irrigation amounts that uniformly improved on the conventional rule for all the testing years, and the largest improvement reached 17% in 2018. The framework is general and applicable to a wide range of cropping systems with realistic optimisation problems.

show abstract

DRLIC: Deep Reinforcement Learning for Irrigation Control

Cited by 13 publications

References 25 publications

Effect of Drip Irrigation Manners and Perlite Application on Water Consumption and Water Use Efficiency for Potato Crop

Effect of Drip Irrigation Manners and Perlite Application on Water Consumption and Water Use Efficiency for Potato Crop

HPC-GPT: Integrating Large Language Model for High-Performance Computing

Deep reinforcement learning for irrigation scheduling using high-dimensional sensor feedback

Contact Info

Product

Resources

About