Hasil untuk "Irrigation engineering. Reclamation of wasteland. Drainage"

Daniel Rodriguez-Cardenas, Xiaochang Li, Marcos Macedo et al.

Large language models for code are advancing fast, yet our ability to evaluate them lags behind. Current benchmarks focus on narrow tasks and single metrics, which hide critical gaps in robustness, interpretability, fairness, efficiency, and real-world usability. They also suffer from inconsistent data engineering practices, limited software engineering context, and widespread contamination issues. To understand these problems and chart a path forward, we combined an in-depth survey of existing benchmarks with insights gathered from a dedicated community workshop. We identified three core barriers to reliable evaluation: the absence of software-engineering-rich datasets, overreliance on ML-centric metrics, and the lack of standardized, reproducible data pipelines. Building on these findings, we introduce BEHELM, a holistic benchmarking infrastructure that unifies software-scenario specification with multi-metric evaluation. BEHELM provides a structured way to assess models across tasks, languages, input and output granularities, and key quality dimensions. Our goal is to reduce the overhead currently required to construct benchmarks while enabling a fair, realistic, and future-proof assessment of LLMs in software engineering.

CHENG Yanan, LI Yanfeng, WANG Fei et al.

【Objective】Atrazine is a widely used herbicide whose ecological impacts on fluvio-aquic soils remain insufficiently understood. This study aims to evaluate the effects of atrazine on soil biogeochemical properties and to identify sensitive biomarkers capable of indicating atrazine pollution level.【Method】A controlled culture experiment was conducted using six atrazine concentrations 0 (CK), 0.6 (T1), 2.5 (T2), 10 (T3), 50 (T4), and 100 mg/kg (T5). The changes in soil enzyme activities (urease, sucrase, amylase, alkaline phosphatase, and catalase) were measured daily from the onset of the experiment to elucidate the temporal variations in their response to atrazine application. The IBRv2 index was used to evaluate the comprehensive toxicity of atrazine to soil biogeochemical processes.【Result】Atrazine significantly stimulated soil urease activity, but the effect varied with atrazine concentration. Soil sucrase activity was significantly inhibited on day 14 after atrazine application but returned to CK levels after 28 days. Increasing atrazine concentrations strongly inhibited soil amylase activity during the early incubation period, with the inhibition positively correlated with atrazine concentration. The activity of alkaline phosphatase did not show a noticeable change in the first 7 days after atrazine application, but became significant between day 14 and day 21 before being inhibited. Atrazine significantly stimulated catalase activity except in T1 treatment, with the activation increasing with atrazine concentration. Soil respiration started to increase significantly 28 days after atrazine application, and it was positively correlated with atrazine concentration. IBRv2 analysis showed that increasing atrazine concentrations resulted in an increase in soil toxicity.【Conclusion】The activity of soil urease, amylase and catalase responded rapidly and sensitively to atrazine application, with the changes in activity level depending on atrazine concentration. These enzymes can serve as biomarkers to assess the impact of atrazine on biogeochemical processes in fluvio-aquic soils.

Oz Levy, Ilya Dikman, Natan Levy et al.

This paper explores how generative AI can help automate and improve key steps in systems engineering. It examines AI's ability to analyze system requirements based on INCOSE's "good requirement" criteria, identifying well-formed and poorly written requirements. The AI does not just classify requirements but also explains why some do not meet the standards. By comparing AI assessments with those of experienced engineers, the study evaluates the accuracy and reliability of AI in identifying quality issues. Additionally, it explores AI's ability to classify functional and non-functional requirements and generate test specifications based on these classifications. Through both quantitative and qualitative analysis, the research aims to assess AI's potential to streamline engineering processes and improve learning outcomes. It also highlights the challenges and limitations of AI, ensuring its safe and ethical use in professional and academic settings.

Lekshmi Murali Rani

The study of behavioral and social dimensions of software engineering (SE) tasks characterizes behavioral software engineering (BSE);however, the increasing significance of human-AI collaboration (HAIC) brings new directions in BSE by presenting new challenges and opportunities. This PhD research focuses on decision-making (DM) for SE tasks and collaboration within human-AI teams, aiming to promote responsible software engineering through a cognitive partnership between humans and AI. The goal of the research is to identify the challenges and nuances in HAIC from a cognitive perspective, design and optimize collaboration/partnership (human-AI team) that enhance collective intelligence and promote better, responsible DM in SE through human-centered approaches. The research addresses HAIC and its impact on individual, team, and organizational level aspects of BSE.

Nibir Chandra Mandal, Oishee Bintey Hoque, Abhijin Adiga et al.

We introduce IrrMap, the first large-scale dataset (1.1 million patches) for irrigation method mapping across regions. IrrMap consists of multi-resolution satellite imagery from LandSat and Sentinel, along with key auxiliary data such as crop type, land use, and vegetation indices. The dataset spans 1,687,899 farms and 14,117,330 acres across multiple western U.S. states from 2013 to 2023, providing a rich and diverse foundation for irrigation analysis and ensuring geospatial alignment and quality control. The dataset is ML-ready, with standardized 224x224 GeoTIFF patches, the multiple input modalities, carefully chosen train-test-split data, and accompanying dataloaders for seamless deep learning model training andbenchmarking in irrigation mapping. The dataset is also accompanied by a complete pipeline for dataset generation, enabling researchers to extend IrrMap to new regions for irrigation data collection or adapt it with minimal effort for other similar applications in agricultural and geospatial analysis. We also analyze the irrigation method distribution across crop groups, spatial irrigation patterns (using Shannon diversity indices), and irrigated area variations for both LandSat and Sentinel, providing insights into regional and resolution-based differences. To promote further exploration, we openly release IrrMap, along with the derived datasets, benchmark models, and pipeline code, through a GitHub repository: https://github.com/Nibir088/IrrMap and Data repository: https://huggingface.co/Nibir/IrrMap, providing comprehensive documentation and implementation details.

Max Neuwinger, Dirk Riehle

The design of effective programming languages, libraries, frameworks, tools, and platforms for data engineering strongly depends on their ease and correctness of use. Anyone who ignores that it is humans who use these tools risks building tools that are useless, or worse, harmful. To ensure our data engineering tools are based on solid foundations, we performed a systematic review of common programming mistakes in data engineering. We focus on programming beginners (students) by analyzing both the limited literature specific to data engineering mistakes and general programming mistakes in languages commonly used in data engineering (Python, SQL, Java). Through analysis of 21 publications spanning from 2003 to 2024, we synthesized these complementary sources into a comprehensive classification that captures both general programming challenges and domain-specific data engineering mistakes. This classification provides an empirical foundation for future tool development and educational strategies. We believe our systematic categorization will help researchers, practitioners, and educators better understand and address the challenges faced by novice data engineers.

LYU Ning, SHI Lei, DAI Yuyu et al.

Saline-alkali soils in Xinjiang are extensive and diverse. Reclaiming these soils for agricultural production plays a critical role in safeguarding food security in China. Exploring reclamation technologies that align with the arid environmental nature and modern water-saving irrigation techniques unique in the region is crucial for the sustainable use of these saline-alkali soils. This paper reviews the historical development and effectiveness of various saline-alkali soil management techniques in Xinjiang, based on literature review and quantitative evaluation of available data. We analyze the bottlenecks in managing saline-alkali soils under the constraints of limited water resources, providing insight into comprehensive utilization strategies for saline-alkali soils in the context of new challenges faced by the region. Based on the balance between water and soil resources, as well as the characteristics of secondary soil salinization in irrigated farmland, we propose an integrated ‘prevention, control, and treatment’ strategy for soil management in watersheds and irrigation districts in the region. Our recommendations include determining rational water resource allocation for irrigation and ecological maintenance, identifying effective techniques to desalinate specific soil layers in drip-irrigated farmlands, establishing dynamic monitoring systems to monitor soil salinization, and implementing prevention-control measures tailored to different types of salinized soils in different areas in the region. These provide a guidance for policymaking to improve management and utilization of saline-alkali soils in Xinjiang.

مهدی رادفر, فرشاد علی‌پور نصیرمحله

ارزیابی مداوم آلودگی آب موضوعی مهم و حیاتی در مدیریت بهینه پهنه‌های آبی است. در این تحقیق به بررسی روند آلودگی نیترات در طول حدود 50‌ کیلومتری از رودخانه تجن، حد فاصل بین ایستگاه هیدرومتری ریگ‌چشمه در بالادست و ایستگاه کردخیل در پایین‌دست در طی سال 1397 پرداخته شد. برای تحقق این امر ابتدا شرایط هیدرولیکی حاکم بر جریان با استفاده از مدل HEC-RAS تعیین و وارد مدل QUAL2Kw شد. پس از واسنجی و صحت‌سنجی‌ مدل، تغییرات زمانی- مکانی آلاینده نیترات در مسیر رودخانه بررسی گردید. نتایج نشان‌ دهنده بیشتر بودن بار ورودی از منابع آلاینده غیرنقطه‌ای و در فصل ‌‌‌کشت به رودخانه بود‌ که سبب بیشتر شدن بار‌ نیترات از حداکثر مجاز می‌گردد. روند افزایش غلظت نیترات در طول مسیر 50‌ کیلومتری در فصل غیرکشت حدود 19 درصد است و حال آنکه به دلیل مصرف بی‌رویه کود در فصل کشت این رقم با افزایش حدود 8/2 برابری به حدود 50‌ درصد می‌‌‌رسد. غلظت نیترات در فصل کشت، در بخش انتهایی و ادامه مسیر جریان به حدود 47 میلی‌گرم بر ‌لیتر رسیده که نزدیک به میزان مجازmg/lit 50 برای کاربری شرب و بسیار بیشتر ازmg/lit 30 برای کاربری کشاورزی بوده که برداشت آب برای کاربری‌های مربوطه را با محدودیت مواجه می‌نماید. از طرفی مناطق پایین‌دست رودخانه که محل تخم‌ریزی ماهیان بوده با روند افزایش نیترات منجر به تغذیه‌گرایی و کاهش جمعیت آبزیان خواهد شد. لذا تعیین چارچوبی برای کاهش و کنترل بار نیترات، با تمرکز بر منابع آلاینده غیر‌نقطه ای در سیا‌ست‌های مدیریتی اکوسیستم آبی رودخانه تجن ضروری است.

J. Al-Jomah, A. Halajnia, A. Lakzian et al.

Introduction Saline soils resulting from natural and/or anthropogenic processes are very diverse and widely distributed under all climates. Soil salinity as a serious environmental problem has negative effects on plant growth and development in arid and semi-arid as well as humid regions. Since increasing global food security is a fundamental goal to feed the growing world population, it is necessary to develop suitable and efficient techniques for the rehabilitation of salt-affected soils and their exploitation. Chemical fertilizers are usually used to provide nutrients required for plant growth in order to increase crop yield, but application of these chemical components has negative environmental effects and reduces the quality of soils and agricultural products. The use of beneficial microorganisms (bacteria and fungi) as fertilizers and biological amendments has a high potential to improve productivity in saline soils. The aim of this study was to investigate the effect of using Acidithiobacillus bacteria along with mycorrhiza on the production of some photosynthetic and biochemical metabolites in maize under salt stress and comparing it with control conditions.   Materials and Methods To perform this experiment, a surface soil sample was collected from a depth of 30 cm from the campus of Ferdowsi University of Mashhad, and some physical and chemical properties of the soil were measured by usual laboratory methods. To prepare saline soil a mixture of four compounds MgSO4.7H2O, Na2SO4, NaCl, and CaCl2. 2H2O were used. The mycorrhizal fungus (Funneliformis mosseae) and mesophilic Acidithiobacillus bacteria species two types of bacteria, Acidithiobacillus thiooxidans PTCC No: 1692 (DSM 504) and Acidithiobacillus ferrooxidans PTCC No: 1646 (DSM 583), were purchased from Turan Biotechnology Company (Semnan Science and Technology Park) and Iran Microbial Scientific and Industrial Research Center (PTCC), respectively. In this research, the effect of biological treatments including: two levels of mycorrhiza (inoculation and non-inoculation), two levels of salinity (0.96 and 6 d/m) and four levels of Acidithiobacillus control (C), Acidithiobacillus thiooxidans (T), Acidithiobacillus Ferrooxidans (F), Acidithiobacillus thiooxidans and Ferrooxidans (T+F) were compared with each other on some photosynthetic and biochemical characteristics of Zea mays under greenhouse conditions in the form of a completely randomized design with factorial arrangement with three replications. 10 gr of salt mixture (this amount of salt was obtained to reach electrical conductivity of 6 in the pre-experiment) was added to 5 kg of soil and the soil moisture of the pots was kept for one month in the field capacity. Bacterial treatments were inoculated with 30 mL of cell suspension per pot (approximately 107 CFU mL-1). In the simultaneous use of two bacteria, 15 ml of each bacterial cell suspension (15+15) was added to each pot. Single-cross 704 variety of maize was grown in pots and soil moisture was maintained during the growth period in the field capacity by weighing. Chlorophyll a, b and carotenoid, concentrations of flavonoids, anthocyanins and proline and electrical leakage were measured in fresh leaf samples (third leaf on the stem).   Results and Discussion The results showed that salinity decreased the percentage of root colonization and chlorophyll a and b content in leaves. Salinity decreased chlorophyll a, b and carotenoid in leaves by 27.9, 68.42% and 50%, respectively. Salinity increased proline concentration (42.62%), electrolyte leakage (33.30%), anthocyanins concentration (96.36%) and leaf flavonoids (84.73%) compared to control soil. Inoculation with mycorrhiza compared to no inoculation had a remarkable and significant effect on all investigated parameters in both saline and control soils. In saline soil, mycorrhizal inoculation reduces electrolyte leakage (56.75%) and increases chlorophyll a (2.3 times), chlorophyll b (6.6 times), carotenoid (1.3 times), proline concentration (24.39%), anthocyanins amount (24.07) and flavonoids (20.4%) in the plant. The effect of bacterial treatments on the investigated parameters in plants inoculated with mycorrhiza was greater than non-inoculated treatments. The effectiveness of the simultaneous application of both bacteria was greater than the effect of each of them alone. In saline soil, simultaneous inoculation of mycorrhizae with both bacteria species reduces electrolyte leakage (14.72%) and increases chlorophyll a (39.80%), chlorophyll b (106%), carotenoid (50%), proline concentration (10.12%), the amount of anthocyanins (14.17%) and flavonoids (4.06%) compared to mycorrhiza treatment alone. The results showed that these bacteria can probably be considered as helping mycorrhizal bacteria.   Conclusion The objective of this study was to examine the impact of simultaneous inoculation of mycorrhizae and Acidithiobacillus bacteria on select photosynthetic and biochemical metabolites of maize subjected to salinity stress conditions. Confirming the results of other studies, the results of this research also showed the clear and distinct effect of mycorrhiza on increasing chlorophyll and producing metabolites effective in increasing plant resistance to salt stress. In addition, the results showed that although the use of each species of Acidithiobacillus ferrooxidans and Acidithiobacillus thiooxidans alone was effective on the measured parameters in both saline and control soils, the simultaneous inoculation of both Acidithiobacillus bacteria species and mycorrhiza had the greatest effect on increasing chlorophyll, production of proline, anthocyanins and flavinoids and reducing electrolyte leakage and as a result, increasing tolerance to salt stress. In other words, these bacteria can be considered as mycorrhiza helper bacteria, whose activity can improve the function of mycorrhiza. On the other hand, mycorrhiza symbiosis may have increased the efficiency of these bacteria by changing the soil conditions and the environment around the roots. However, further greenhouse and field experiments with other plant species are necessary to confirm these findings.

Ramla H. Melo, Moch R. Pambudi, Alim Niode

Lake Limboto, situated in Gorontalo, Indonesia, confronts severe threats jeopardizing its sustainability. Widespread deforestation in the watershed area has led to excessive sedimentation within the lake, consequently diminishing its water storage capacity and compromising its flood control function. This degradation has manifested itself in downstream droughts during the dry season and flooding during the rainy season. Historical data reveals a stark reduction in Lake Limboto’s size, plummeting from approximately 3,644.5 ha in 1991 to around 2,693.9 ha in 2017. This study aims to provide comprehensive examination of the interplay between the socioeconomic status of the local community and their understanding of the lake ecosystem. Furthermore, it delves into how these factors produce synergies that shape and impact community involvement in sustainable lake management initiatives. Hypothesis testing yielded significant results, affirming the existence of a positive correlation between socioeconomic status, knowledge of the lake ecosystem, and active community participation in sustainable lake management efforts. The findings underscore the critical importance of socioeconomic factors that need to be considered when designing strategies for the preservation and sustainable management of Lake Limboto. Integrating the community into conservation initiatives is necessary, given their intrinsic relationship with the lake. By acknowledging and leveraging the nexus between socioeconomic status, ecological knowledge, and active participation, stakeholders can formulate more effective and inclusive strategies for safeguarding Lake Limboto’s ecological integrity. This study contributes valuable insights for policymakers, environmentalists, and local communities alike, emphasizing the necessity of collaborative efforts to ensure the long-term resilience and vitality of Lake Limboto.

Amjad Mizyed, Yunes Mogheir, Mazen Hamada

Water pollution and scarcity are amongst the most pressing challenges affecting the water environment in the Gaza Strip. Agricultural activities play an important role in this issue, consuming more than 50% of the extracted water, while contributing to environmental degradation through the excessive use of pesticides and fertilisers. The grey water footprint (GWF) was quantified to evaluate pollution from crops using the Hoekstra methodology. The grey water totalled 30.63 mln m3 , with 51% attributed to vegetables, 44.5% to horticultural trees, and 4.5% to field crops between 2018 and 2022. An evaluation of the sustainability of the water footprint revealed that the assimilation capacity of water resources has been completely consumed. As a result, the Gaza Strip is classified as an unsustainable area, which is a serious violation of globally approved water quality standards. To optimise the grey water footprint, the nitrogen balance, N-leakage rate, and associated uncertainties were analysed using fractional programming, leading to the development of a model aimed at achieving optimal results. The findings show the importance of implementing this approach in the Gaza Strip, enabling policymakers and local authorities to develop a promising strategy for agricultural practices. This would promote sustainable and effective management of water resources and a safe and productive agricultural environment.

رضا الهی, مهدی قمشی, محمدرضا زایری

پدیده جریان غلیظ زمانی رخ می‌دهد که سیالی به‌دلیل اختلاف چگالی درون سیال دیگر حرکت کند. هنگامی‌که چگالی سیال بیشتر از چگالی سیال پیرامون باشد، جریان زیرگذر رخ می‌دهد. در جریان‌های غلیظ در ناحیه تماس جریان با سیال پیرامون، ناپایداری جریان در مرز بین دولایه عامل ورود سیال پیرامون به درون جریان غلیظ می‌شود. ناحیه غوطه‌وری یکی از نواحی چهارگانه جریان‌های غلیظ زیرگذر است که بیشترین میزان ورود سیال پیرامون به درون جریان غلیظ را داراست. در این تحقیق رفتار جریان‌های غلیظ نمکی در قوس‌ها مورد مطالعه قرار گرفت. نتایج نشان می‌دهد که افزایش شعاع انحنا منجر به کاهش نیروی گریزازمرکز و زیاد شدن سرعت در راستای جریان گشته و این امر افزایش شدت اختلاط را موجب می‌شود. هرقدر بر چگالی سیال غلیظ افزوده شود تمایل آب زلال ساکن برای نفوذ به درون آن کاهش می‌یابد. همچنین در زمینه ورود سیال پیرامون به درون جریان غلیظ رابطه‌ای ارائه‌شده است که نشان میده حداکثر 40 درصد دبی سیال‌پیرامون می‌توان وارد جریان غلیظ در ناحیه غوطه‌وری گردد.

Bernard T. Agyeman, Benjamin Decard-Nelson, Jinfeng Liu et al.

This paper proposes a Semi-Centralized Multi-Agent Reinforcement Learning (SCMARL) approach for irrigation scheduling in spatially variable agricultural fields, where management zones address spatial variability. The SCMARL framework is hierarchical in nature, with a centralized coordinator agent at the top level and decentralized local agents at the second level. The coordinator agent makes daily binary irrigation decisions based on field-wide conditions, which are communicated to the local agents. Local agents determine appropriate irrigation amounts for specific management zones using local conditions. The framework employs state augmentation approach to handle non-stationarity in the local agents' environments. An extensive evaluation on a large-scale field in Lethbridge, Canada, compares the SCMARL approach with a learning-based multi-agent model predictive control scheduling approach, highlighting its enhanced performance, resulting in water conservation and improved Irrigation Water Use Efficiency (IWUE). Notably, the proposed approach achieved a 4.0% savings in irrigation water while enhancing the IWUE by 6.3%.

Tian Liu, Liuyi Jin, Radu Stoleru et al.

Current state-of-the-art residential irrigation systems, such as WaterMyYard, rely on rainfall data from nearby weather stations to adjust irrigation amounts. However, the accuracy of rainfall data is compromised by the limited spatial resolution of rain gauges and the significant variability of hyperlocal rainfall, leading to substantial water waste. To improve irrigation efficiency, we developed a cost-effective irrigation system, dubbed ERIC, which employs machine learning models to estimate rainfall from commodity doorbell camera footage and optimizes irrigation schedules without human intervention. Specifically, we: a) designed novel visual and audio features with lightweight neural network models to infer rainfall from the camera at the edge, preserving user privacy; b) built a complete end-to-end irrigation system on Raspberry Pi 4, costing only \$75. We deployed the system across five locations (collecting over 750 hours of video) with varying backgrounds and light conditions. Comprehensive evaluation validates that ERIC achieves state-of-the-art rainfall estimation performance ($\sim$ 5mm/day), saving 9,112 gallons/month of water, translating to \$28.56/month in utility savings. Data and code are available at https://github.com/LENSS/ERIC-BuildSys2024.git

علی شاهنظری, درسا دریکنده, فاطمه جعفری صیادی et al.

در مطالعه حاضر، به منظور بهره‌برداری بهینه از منابع آب و خاک استان مازندران متناسب با پتانسیل منطقه، از روش تطبیقی- مقایسه‌ای استفاده شد. بدین منظور ابتدا به شناسایی وضع موجود استان در قالب منابع آب و خاک و الگوی کشت پرداخته شد و در گام بعد با مقایسه و انطباق دیگر مناطق جهان که از نظر اقلیمی شرایطی مشابه با استان مازندران دارند، الگوبرداری از تجربیات آن کشورها در زمینه کشت محصولات متناسب با پتانسیل منطقه، صورت پذیرفت. نتایج حاصل از فاز تطبیق نشان داد که در مجموع 158 نقطه بر روی زمین تراز اقلیمی مشابه با استان مازندران داشتند. بر اساس نتایج تطبیقی مقایسه‌ای به دست آمده، الگوی کشت فعلی در استان مازندران باید متناسب با منابع آب و خاک، اندکی تغییر یابد. سطح زیر کشت محصولاتی همچون پنبه که در گذشته نیز در این استان مورد پسند کشاورزان بوده است می‌تواند به عنوان محصولی مناسب برای صنایع نساجی، دوباره در این استان افزایش پیدا کند. همچنین درختی چون زیتون که قابلیت استفاده در زمینه‌های مختلف (خام‌خوری، روغن‌گیری و علوفه دام) دارد و با توجه به اینکه در اقلیم مازندران در بسیاری از مناطق کوهپایه‌ای این استان گونه‌های روغن‌گیری زیتون عملکرد مناسبی از خود نشان داده‌، این محصول نیز قابل پیشنهاد است. همچنین امکان‌پذیری کشت چند محصول جدید در استان مازندران که از طریق مصاحبه با اساتید دانشگاه علوم کشاورزی و منابع طبیعی ساری و بررسی طرح‌های پژوهشی نیز انجام شده که محصولاتی مانند گیاهان دارویی نیز پیشنهاد می‌گردد.

HU Huiling, WANG Feng, FENG Quanqing et al.

【Objective】 Soil moisture sensors have been increasingly used in different fields to measure soil water content at high temporal resolution, but its reliability depends on many factors. In this paper, we investigate the effect of soil salinity on their accuracy. 【Method】 The laboratory experiment was conducted at the Irrigation Test Station of the First Division of Xinjiang Alaer Corps. FDR and TDR sensors were used in the experiment. We compared five salinity treatments: 2, 3, 5, 7, 9 mS/cm; the soil moisture was adjusted to the field capacity followed by natural evaporation. The absolute error (AE), relative error (RE) and standard deviation (SD) were used to evaluate the accuracy and consistency of the sensors. 【Result】 Soil moisture and salinity both affected accuracy and consistency of the sensors. Without calibration, the accuracy of the CSF11 and ML2x sensors was high and measurements were consistent, while the EC-5 and TDR305H sensors were less accurate and consistent due to the combined influence of soil salinity and moisture. Calibration significantly improved the accuracy and consistence of all four sensors. 【Conclusion】 Considering accuracy and consistency, the expensive ML2x sensors worked best when salt content does not exceed 9 mS/cm. The less expensive CSF11 sensors also worked well when soil salt is low. The EC-5 sensors can measure soil moisture reasonably well for soil with moderate and high salinity. When the soil moisture is less than 20 cm3/cm3, TDR305H sensors is accurate and reliable.

فاطمه مقدسی, مهنوش مقدسی, مهدی محمدی قلعه نی

در این پژوهش هدف ارزیابی پایگاه داده­های بارش با مقادیر مشاهداتی به‌صورت زمانی (ماهانه و فصلی) و مکانی (دو حالت نقطه­ای (40 ایستگاه سینوپتیک) و سطحی (30 حوضه آبریز درجه دو و چهار اقلیم))، در کشور به‌عنوان منطقه مطالعاتی می­باشد. بدین منظور ابتدا داده­های مشاهداتی (100 ایستگاه در مقیاس روزانه) و پایگاه­های جهانی بارش شامل ERA5، MRRRA2، GLDAS و TERRA (با تفکیک مکانی مختلف در مقیاس ماهانه) طی دوره زمانی 1398-1366 گرد­آوری و استخراج گردید. سپس براساس شاخص خشکی، طبقه­بندی اقلیمی ایستگاه­ها و حوضه­ها انجام شده است. ارزیابی دقت پایگاه‌ها با استفاده از معیارهای ضریب همبستگی (R)، میانگین خطای اریبی (MBE) و مجذور میانگین مربع خطا استانداردشده (NRMSE) استفاده شده است. نتایج معیارهای در بارش ایستگاهی نشان داد که پایگاه TERRA در همه فصول به‌جز تابستان و در اقلیم­های فراخشک، خشک و نیمه‌خشک، با متوسط 70 درصد ضریب همبستگی بالاتر از 5/0 (R) و میزان خطای 90 درصد کم‌تر از 5/0 (NRMSE) نسبت به بقیه­ها پایگاه­ها و در اقلیم مرطوب پایگاه ERA5 عملکرد بهتری را از خود نشان داد. در بارش حوضه­ای نیز نشان داد به‌ترتیب پایگاه TERRA در اقلیم فرا­خشک، پایگاه­های ERA5، MRRRA2، GLDAS  و TERRA در اقلیم خشک، پایگاه­های ERA5 و TERRA در اقلیم نیمه‌خشک و پایگاه‌های ERA5، TERRA و MERRA2 در اقلیم مرطوب با متوسط 80 درصد ضریب همبستگی بالاتر از 5/0 و میزان خطای 70 درصد کم‌تر از 5/0 کارایی مناسب‌تری را نشان دادند. به‌طور کلی پایگاه TERRA در حالت نقطه­ای، سطحی و اقلیمی از عملکرد خوبی برخوردار بوده است که می‌توان گفت به‌علت دقت مکانی بالای آن بوده باشد.

Abdorreza Vaezihir, Vahede Aghaie, Mehri Tabarmayeh

IntroductionDetermining the capture zone of water resources is a strategic approach proposed at the national level of water resources management in Iran. One of the important actions for this purpose is protection of karst water resources, which are considered one of the vital sources for supplying water due to the widespread karst formations in this country and the limitation of groundwater resources in alluvial aquifers. Generally, water flows out through the springs in the karst system. The land area where the water contributes to the spring is called the spring's capture zone. The study and analysis of the recession curve of the springs, the area extending from a discharge peak to the base of the next rise, along with the other physical characteristics of springs such as electrical conductivity is a useful indicator for getting knowledge about the condition of the catchment area and other properties of the heterogeneous karst terrain. In estimating the water budget, unlike the non-karst areas where the surface runoff or the outflow is considered the main factor in the estimated water budget, the recharge component is an important factor in the karst domain. The difference between hydrogeological and hydrological (topographic) catchments is one of the obvious features in karst landscapes. The identification of these basins or their boundaries is possible by combining geology and topography information. Soufiyan Cement Company in the vicinity of Chelleh Khanehe Olya spring located in Moro Mountain is associated with the creating social problems due to the expansion of mining activities and the negative impact on spring water in this area. Therefore, this study aims to determine the catchment area and the capture zone of the Chelleh Khanehe Olya spring by determining the protective boundary for the extraction of limes by the Soufiyan cement factory to prevent the negative impact of this factory on the spring.Materials and MethodsIn this research, the hydrograph of the recession curve related to a rainfall event has been analyzed by taking into account the mean monthly discharge rate of spring to determine the sub-regimes of diffuse and conduit flow by employing the following equation:Qt=Q0e-αt                          (1)Where Qt is the discharge rate at time t, Qo reveals the discharge at the initial time, and α is a recession coefficient.In addition, The Qmax/Qmin ratio has been calculated to estimate the flow type and the degree of karstification in the catchment area.In the next step, to determine the Chelleh Khanehe Olya spring catchment area and its capture zone, spring hydrogeological boundaries were determined and investigated using the SCS method and estimating the area's water budget. Due to the lack of sufficient rainfall and groundwater discharge information in this region, the water budget for a given period (2019-2020) has been computed indirectly by measuring the monthly discharge rate from the selected stations. After collecting the required data, the following equation developed by Milanovich (1989) has been used to estimate the water budget as follows:P=E+R+I                          (2)Where P, E, R, and I denote precipitation (P), evaporation at the basin level (E), runoff (R), and recharge to the aquifers (I). All the parameters are in mm units.Results and DiscussionAnalyzing the variation of electrical conductivity along with the discharge rate indicates that by decreasing the discharge rate from 2.5 l/s to 8.1 l/s, the electrical conductivity increase from 463 µs/cm to 500 µs/cm, reflecting an increase in the volume of the reservoir, the dilution of the aquifer. The hydrograph recession curve during 2019-2020 indicated two laminar and turbulent sub-regimes. Micro regimes α1 (01.002) and α2 (0.013) represented that the dominant system of karst development in the region is diffuse. The high density of fractures and the lack of purity of lime are the main reasons for the weak development of the karst fracture in the region, which the Chelekhaneh Alia spring recession curve analysis,  maximum to minimum ratio of discharge, and karstification coefficient confirmed this issue. Determining the catchment basin using geological, hydrogeological information, and water budget showed that the hydrological and hydrogeological boundary of the spring is different. The protected zone of Chelekhane Alia spring, which includes the total hydrogeological basin and the Cretaceous limestone area below the level of the spring, was estimated to be about 184,000 square meters (18 hectares). According to the findings of this research, Sufian Cement Factory does not have the right to enter the hydrogeological boundary to extract limes, and on the other hand, to prevent the water level from decreasing due to the excessive extraction of lime as a result of the excavation depth reaching the level of the water table, it suggests to extract from the unsaturated part of the aquifer (unsaturated limes) to prevent the flow rate of Chele Khana spring from decreasing and even drying it up.ConclusionAnalyzing the discharge rate, electrical conductivity, hydrograph recession curve, and its recession coefficient(α=0.002), revealed that the dominant flow in the system is diffuse, which results from the high density of fractures and region lithology consisting of impure cretaceous limestone. Since the result revealed the inconsistency between hydrological and hydrogeological boundaries, the geological profile of the site was prepared and the spring of the catchment was estimated. Based on the findings of this research, the Chelle Khanehe Olya capture zone consists of the hydrogeological area, obtained from the groundwater budget estimation, and the protective boundary for the limestone below Cheleh Khaneh Olya spring (the unsaturated zone of the area's limestones), which covers an area of about 18 hectares.

Bernard T. Agyeman, Mohamed Naouri, Willemijn Appels et al.

The agricultural sector currently faces significant challenges in water resource conservation and crop yield optimization, primarily due to concerns over freshwater scarcity. Traditional irrigation scheduling methods often prove inadequate in meeting the needs of large-scale irrigation systems. To address this issue, this paper proposes a predictive irrigation scheduler that leverages the three paradigms of machine learning to optimize irrigation schedules. The proposed scheduler employs the k-means clustering approach to divide the field into distinct irrigation management zones based on soil hydraulic parameters and topology information. Furthermore, a long short-term memory network is employed to develop dynamic models for each management zone, enabling accurate predictions of soil moisture dynamics. Formulated as a mixed-integer model predictive control problem, the scheduler aims to maximize water uptake while minimizing overall water consumption and irrigation costs. To tackle the mixed-integer optimization challenge, the proximal policy optimization algorithm is utilized to train a reinforcement learning agent responsible for making daily irrigation decisions. To evaluate the performance of the proposed scheduler, a 26.4-hectare field in Lethbridge, Canada, was chosen as a case study for the 2015 and 2022 growing seasons. The results demonstrate the superiority of the proposed scheduler compared to a traditional irrigation scheduling method in terms of water use efficiency and crop yield improvement for both growing seasons. Notably, the proposed scheduler achieved water savings ranging from 6.4% to 22.8%, along with yield increases ranging from 2.3% to 4.3%.

Bishal Lakha, Kalyan Bhetwal, Nasir U. Eisty

Context: On top of the inherent challenges startup software companies face applying proper software engineering practices, the non-deterministic nature of machine learning techniques makes it even more difficult for machine learning (ML) startups. Objective: Therefore, the objective of our study is to understand the whole picture of software engineering practices followed by ML startups and identify additional needs. Method: To achieve our goal, we conducted a systematic literature review study on 37 papers published in the last 21 years. We selected papers on both general software startups and ML startups. We collected data to understand software engineering (SE) practices in five phases of the software development life-cycle: requirement engineering, design, development, quality assurance, and deployment. Results: We find some interesting differences in software engineering practices in ML startups and general software startups. The data management and model learning phases are the most prominent among them. Conclusion: While ML startups face many similar challenges to general software startups, the additional difficulties of using stochastic ML models require different strategies in using software engineering practices to produce high-quality products.