Research & reports

Yizhi Zhang · · Global

This report systematically reviews the environmental performance of rooftop greenhouses, focusing on life cycle assessment (LCA) approaches. The review found that existing studies are limited, often case-specific, and use diverse methodologies, hindering comparisons. Environmental performance is highly context-dependent and influenced by methodological assumptions, with conventional LCA often failing to capture dynamic interactions between greenhouse operations, crop growth, and host buildings, leading to an incomplete representation of environmental performance.

Kelvin Kekeli Kobla Ahiakpor, David Ebo Adjepon‐Yamoah · DMPedia Lecture Notes in Computer Science & Engineering · Ghana

This paper presents Cultivate, an AgroAgent-as-a-Service (AaaS) platform designed to scale agricultural extension services in Ghana by allowing agronomists to deploy configurable AI agents. A pilot study with one agronomist and one farmer from Farmitecture, a Ghana-based urban farming startup, validated the system. The agronomist configured an agent in under ten minutes and estimated it could handle 50-60% of queries, while the farmer found responses specific and grounded. The pilot demonstrated the technical feasibility and positive reception of decentralized, agronomist-trained AI agents, noting limitations such as a small pilot sample and lack of WhatsApp integration.

Vidyashree K P, Udayabalan B, Shilpa M S, Madhusudhana R, Nandini S, Bhagyalakshmi R, Shivani T J · Journal of Integrated Science and Technology · Global

This research proposed a plant species recognition system based on deep learning technology to guide plant selection and management in rooftop gardening and urban agriculture. The system comprises four steps: image acquisition, preprocessing, feature extraction, and classification. The model was trained on a dataset of 80,000 images of 14 plant species, utilizing transfer learning on a ResNet9 architecture. The model achieved a score of approximately 92 out of 100.

Lovina Yogarajan, Mohammad Masukujjaman, Abdullah Al Mamun, Mohd Helmi Ali · Journal of Agribusiness in Developing and Emerging Economies · Malaysia

An online survey of 250 urban residents across various regions of Malaysia investigated factors influencing the adoption of hydroponic farming. Findings indicate that attitude, hydroponic compatibility, and perceived trust significantly influence adoption intentions, and intention strongly influences actual adoption. However, performance expectancy, effort expectancy, and social influence did not significantly impact adoption intentions.

Mohammed El-Hajj · Frontiers in Sustainable Food Systems · Global

This conceptual paper proposes the Urban Agriculture Digital Twin (UA-DT), a four-layer cyber-physical framework combining IoT sensing, cloud infrastructure and hybrid mechanistic/AI models for real-time monitoring and city-scale food-system simulation, with logical feasibility demonstrated through an illustrative software simulation (Eclipse Ditto, Azure IoT, Python) for a community rooftop garden. The paper cites benchmark ranges — 20–40% water savings, 15–25% fertilizer reduction, up to 30% post-harvest loss reduction, and 3–7 day early-warning lead time — as literature-derived projections that a fully validated UA-DT deployment would be expected to approach, explicitly noting these are not empirical findings of this study.

Yuvaraja Boovanahalli Kariyappagowda, Khateeja Ambareen, S P Vijaya Vardan Reddy, Chethan Bommalingaiahanapalya Krishnamurthy, Madhu Puttegowda · Journal of Asian Scientific Research · Global

This study developed a machine learning-based leaf-disease detection system to help rooftop gardeners and small-scale growers, aiming to address plant-disease spread and delayed diagnosis that leads many gardeners to abandon increasingly popular rooftop gardening in space-limited urban areas. Using image segmentation as a preprocessing step followed by a classification model, and trained and tested on leaf images from five commonly cultivated species -- guava, jamun, lemon, mango and pomegranate -- the system achieved an overall accuracy of 1.00, with lemon and mango disease classification reaching accuracies of 0.995 and 0.991 respectively and F1-scores exceeding 0.88.

Yogi Priyo Istiyono, Siti Rokhmanila, Ojak Abdul Rozak · Jurnal Otomasi Kontrol dan Instrumentasi · Global

Researchers developed and experimentally evaluated an IoT-based monitoring and automatic irrigation system for small-scale and urban farming, built around a NodeMCU ESP8266 microcontroller with capacitive soil moisture, soil pH, and DHT11 temperature sensors, transmitting data via Wi-Fi to the Blynk cloud platform with a smartphone interface and 16×2 LCD, and a relay-controlled 5V DC pump triggered by preset soil moisture thresholds. Validated against a reference instrument (ETP-302), the system showed average measurement errors of 3.4% for soil moisture, 4.1% for soil pH, and 2.8% for temperature, and irrigation activated within a dry-soil range of 430-520 ADC and stopped automatically once sufficient moisture was reached.

Dawan Arkini Challam · Asian Research Journal of Agriculture · Global

A low-cost vertical farming system was built from 90 mm PVC pipes arranged in a three-tier frame, using soil as the primary growing medium, to grow strawberries (Fragaria × ananassa) under a semi-controlled microclimate created by 50% shade netting during the vegetative stage. Shading reduced transpiration stress and improved moisture retention, promoting leaf development, and removing the shade at the onset of flowering increased floral initiation and the number of flowers per plant, attributed to improved light availability. This stage-specific light management raised leaf, flower and fruit counts and yield by combining features of open-field and protected cultivation, though the abstract does not report the number of plants tested or whether the trial was replicated.

Akhil S Anand, Hannes Pravida, Fredrik Fossan-Waage, Tormod Skorpe Skjolden, Giulia Robbiani, Younes Zahraoui, Emil Wolff Anthony, Jayaprakash Rajasekharan, Sissel Torre, Knut Asbjørn Solhaug, Sebastien Gros · Frontiers in Horticulture · Global

A paper on vertical farming — a controlled-environment agriculture system — examines its potential integration with energy markets. It states that vertical farming's economic viability is constrained by high capital and operational costs, a substantial share of which is energy expenditure, and explores how vertical farms could participate in day-ahead, balancing, and flexibility energy markets by adjusting lighting and climate-control energy use in response to market signals, potentially reducing costs and generating additional revenue. It identifies gaps in understanding of plant responses to variable lighting as a critical barrier to implementation and illustrates these integration challenges through small-scale laboratory experiments.

Paul Emile Tchinda, Thi-Thanh-Hiên Pham · Canadian Geographies / Géographies canadiennes 70(3) · Cameroon (one large and one medium-sized city)

Urban agriculture appears in many sustainability agendas yet has been ignored in the public policies of many African countries. Combining multi-scale mapping (city and neighbourhood) with semi-structured interviews in one large and one medium-sized Cameroonian city, this study tests how well those techniques characterise urban agriculture for local decision-making. Mapping from 5-metre SPOT satellite imagery gives a general grasp of the spatial distribution of practices, but crop types, emerging entrepreneurial practices and the temporality of crops are invisible to it and surface only through field mapping and interviews. Echoing critical remote-sensing scholarship, the authors propose a methodological framework for profiling urban agriculture and argue that the choice of research method shapes our understanding of it, so it should be made with each city's specific characteristics in mind.

Paul Β. Thompson · · Global

This article discusses urban agriculture, noting that the decline of grocery stores in inner cities and projected vulnerabilities in megacities outside the global West suggest distinct moral imperatives. It contrasts urban agriculture with rural resilience and sustainable intensification, highlighting its focus on consumption and present needs. The article describes two urban agriculture archetypes: one embracing high-tech solutions and another emphasizing local solidarities and urban-based control over the food system.

Gokulakrishnan G, Navaneetha Krishnan T, Tamilselvan D, S Sanjeevkumar, Devaganesh A, Janani N, K. Arunadevi, Balaji Kannan · Madras Agricultural Journal · Global

This review explores vertical farming, a method that uses stacked layers in controlled environments for year-round crop production with reduced resource use. It assesses the environmental and economic advantages of vertical farming, while critically examining its limitations, including high energy demands and limited crop diversity. The study highlights that despite its potential, vertical farming faces challenges regarding economic viability due to high energy consumption.

André Luiz dos Santos, Bruno Teixeira Lima, Leonardo Cabral Ramos, Lucas Bellio Buldrini, Lucas Ferreira de Queiroz, Henrique Silva, Paulo César da Silva Emanuel, Gustavo Caravita de Andrade · DELOS Desarrollo Local Sostenible · Global

This work presents AquaGarden, an automated irrigation system with soil temperature and humidity monitoring, developed using an ESP32 microcontroller and physical sensors. Collected data is sent to a FlutterFlow mobile application connected to Firebase for cloud storage and remote management. The system aims to facilitate garden cultivation through automation, optimizing water usage and reducing manual intervention, allowing real-time monitoring and remote irrigation control.

Imran Ali Lakhiar, Haofang Yan, Tabinda Naz Syed, Chuan Zhang, Sher Ali Shaikh, Md Rakibuzzaman, Rahim Bux Vistro · Horticulturae · Global

A systematic review of soilless farming (SLF) systems globally identified their role in enhancing horticultural resilience in urban and peri-urban settings. SLF offers advantages like water conservation and increased yield, but faces significant challenges. High setup costs, substantial energy demands, and the requirement for specialized technical expertise continue to limit its widespread adoption.

Olufemi A. Omitaomu, Ali Mostafavi, Sukanya Randhawa, Haoran Niu · SIGSPATIAL Special · Global

Urban AI is an interdisciplinary field integrating artificial intelligence, spatial computing, and urban science to address urbanization challenges. The growth of urban data and digitization of city infrastructures create opportunities for data-driven machine learning in urban science. Urban AI focuses on innovative AI applications for urban problems, developing AI-ready urban data infrastructures, and practical urban applications across areas like urban planning, traffic forecasting, energy optimization, public safety, urban agriculture, and land use management.

Fadhil Ahla Firdaus, Siti Nurlaela, Mastur Mastur · Journal of Agribusiness Science and Rural Development · Global

This qualitative descriptive study analyzed Instagram insights for the @great.andgreen account from November 20, 2023, to April 28, 2025, to understand its role in digital empowerment for urban farming communities. The account showed positive growth with 1,335 followers, 130,413 impressions, and 18,991 reach, primarily among 18-24 year olds. Content interaction reached 2,215, indicating potential for expanding influence beyond main followers.

Amjad Aljuhani, Rahaf Baghdadi, Wafaa Alzahrani, Deemah Aljuhani · · Saudi Arabia

This study examined the feasibility of vertical farming in Saudi Arabia, using mathematical optimization to identify optimal locations. A mixed-integer linear programming model, developed with AIMMS software, incorporated infrastructure compatibility, water availability, and energy consumption. Results identified seven optimal locations across five cities—Riyadh, Jeddah, Dammam, Tabuk, and Khamis Mushait—ensuring efficient lettuce production at minimized costs. However, challenges such as high energy requirements and initial investment costs persist.

Kit Hoe Chan · DR-NTU (Nanyang Technological University) · Singapore

This thesis explores the architecture, applications, and challenges of Internet of Things (IoT)-based urban farming systems, focusing on their role in enhancing agricultural productivity in densely populated environments. IoT integrates smart sensors, data analytics, and automation for real-time monitoring and precise control of crop environments, optimizing resource use and increasing yield consistency. The study highlights how IoT supports resilient, resource-efficient, and scalable smart-city agriculture, with future potential for AI-based predictive analytics and blockchain-enabled traceability.

Paola Lassandro, Salvatore Capotorto, Valeria Mammone · Sustainability · Global

This study explored smart, low-cost cultivation systems for building facades as nature-based solutions to improve energy efficiency and urban food production. An eco-smart irrigation system, achieving up to 57.14% water savings, was implemented in a vertical green module. This system reduced internal temperatures by 3–4 °C in an office room during hot days in a Mediterranean city.

José Cleydson F. Silva, Kleiton Lima de Godoy Machado, Anna Flavia de Souza Silva, Raquel Dias, Victor Ricardo Bodnar, Wallison Oliveira Vieira, María Alejandra Moreno-Pizani, Jenifer Dias Ramos, Ivani Pauli, Lucas Cavalcante da Costa · Sustainability · Global

This global review explores innovative advancements in agriculture and food technology, including urban farming, regenerative agriculture, agroforestry, and food production in extreme environments. It examines advances in biotechnology, synthetic biology, nanotechnology, and the role of AI in precision farming to improve crop yields and nutrition. The review also discusses the importance of policy, regulation, and community-driven approaches for a resilient global food system.

Anand A. Jose, S. Mahalakshmi, S Arjun · · Global

This paper explores the integration of precision farming methods in urban landscapes to address food insecurity and achieve zero hunger goals. Precision farming utilizes advanced technologies to optimize crop production, resource allocation, and environmental sustainability. The paper scrutinizes the concept of precision farming, its applicability in urban contexts, diverse techniques suitable for urban agriculture, and showcases successful case studies.

Sadiq Ur Rehman, Muhammad Adeel Mannan, Muhammad Ahsan Shaikh, Muhammad Uzair · Memoria Investigaciones en Ingeniería · Pakistan

In Pakistan, an IoT-based solar-powered smart vertical farming system was proposed to address agricultural challenges like water scarcity. A six-week trial cultivating cherry tomatoes showed the system achieved a 60-65% yield increase, 40% energy saving, and 28.57% water consumption reduction compared to traditional methods. However, limitations included the small trial size and lack of long-term environmental impact data, and scalability challenges such as cost, maintenance, and local restrictions need to be addressed for wider adoption.

Wafaa Radi · Journal of Communication Sciences and Information Technology · Global

Many existing IoT-based hydroponic control systems limit user customization due to tightly coupled hardware and software. This paper proposes Hydro-smart, a modular and user-friendly IoT platform designed for small-scale DIY enthusiasts and medium-scale urban agriculture practitioners. Hydro-smart aims to automate and optimize gardening processes, facilitate agricultural experimentation, and enable users to act as citizen scientists by simplifying experimental design and automating data collection.

Zakhro Sodikova · International Journal of Scientific Research in Computer Science Engineering and Information Technology · Global

This research proposed and aimed to design and implement a Machine Learning-Based Climate-Adaptive Smart Gardening System for sustainable urban agriculture. The system uses environmental sensors to record soil moisture, air temperature, humidity, solar exposure, and light intensity in real-time. It employs machine learning models like Gradient Boosting, Random Trees, and LSTM to predict irrigation needs, plant stress, and environmental changes, adjusting gardening conditions to mitigate climate impacts.

Fadilla Siska Tiara, Eva Maria Sulastri · BUDIMAS JURNAL PENGABDIAN MASYARAKAT · Malaysia (Kuala Lumpur)

Training on planting mustard greens using the hydroponic wick system was conducted for students of Universitas Singaperbangsa Karawang and University Teknologi Mara at the AU2 Keramat Community Garden in Kuala Lumpur, Malaysia. The training aimed to improve understanding and skills in hydroponics, raise awareness of vegetable consumption, and foster an entrepreneurial spirit. Pre- and post-tests showed significant improvement in participants' knowledge regarding hydroponics benefits, planting media, and wick system manufacturing techniques.