Climate change is impacting the ecological, social and technological aspects of urban gardens. Gardens experience threats (e.g., water scarcity) but are also responding through adaptation strategies (e.g., selecting drought-resilient plants). A synthetic overview of how urban gardens are affected by climate change and responding to climate change is unclear. Here, we systematically reviewed articles and book chapters published in the last two decades (2000–2022) to illustrate the relationship between climate change and urban gardening. From 72 documents analyzed with Nvivo Software, we found that there has been an increase in academic publications. Universities from the US (14) and Germany (9) universities are the dominant producers. Evidence shows that climate change can have negative impacts on cities, people and urban food. Suggestions on how to build the adaptation capacity of urban gardens include collecting rainwater, changing plant selection, changing planting times, applying vegetative cover on the soil and other practices. For cities, community and allotment gardens are helpful for adaptation, mitigation and resilience. This includes the capacity to regulate the microclimate, to reduce urban heat island effects and to buffer urban floods, the power to capture carbon, the ability to create social networks and other socio-environmental benefits for urban climate planning.

Weeds are unwanted and invasive plants that proliferate and compete for resources such as space, water, nutrients, and sunlight, affecting the quality and productivity of the desired crops. Weed detection is crucial for the application of precision agriculture methods and for this purpose machine learning techniques can be used, specifically convolutional neural networks (CNN). This study focuses on the search for CNN architectures used to detect and identify weeds in different crops; 61 articles applying CNN architectures were analyzed during the last five years (2019–2023). The results show the used of different devices to acquire the images for training, such as digital cameras, smartphones, and drone cameras. Additionally, the YOLO family and algorithms are the most widely adopted architectures, followed by VGG, ResNet, Faster R-CNN, AlexNet, and MobileNet, respectively. This study provides an update on CNNs that will serve as a starting point for researchers wishing to implement these weed detection and identification techniques.

Artificial lighting is essential in indoor agriculture, directly influencing plant growth and productivity. Optimizing its use requires advanced technologies that improve light management and adaptation to crop needs. This systematic review, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, examines recent advancements in artificial lighting technologies, focusing on their applications, challenges, and future directions. A systematic search in Web of Science (WOS) and Scopus identified 70 relevant studies published between 2019 and 2024. The analysis highlights five major technology groups: (i) lighting control systems, with Light-Emitting Diodes (LEDs) as the dominant solution; (ii) Internet of Things (IoT) incorporating sensors, deep neural networks, Artificial Intelligence (AI), digital twins, and machine learning (ML) for real-time optimization, as well as communication technologies, enabling remote control and data-driven adjustments; (iii) simulation and modeling tools, refining lighting strategies to enhance plant responses and system performance; and (iv) complementary energy sources, improving lighting sustainability. IoT-driven automation has significantly improved artificial lighting efficiency, optimizing adaptation and plant-specific management. However, challenges such as system complexity, high energy demands, and scalability limitations persist. Future research should focus on refining IoT-driven adaptive lighting, improving sensor calibration for precise real-time adjustments, and developing cost-effective modular systems to enhance widespread adoption and optimize resource use.

Advancements in polymer science and nanotechnology hold significant potential for addressing the increasing demands of food security, by enhancing the shelf life, barrier properties, and nutritional quality of harvested fruits and vegetables. In this context, biopolymer-based delivery systems present themselves as a promising strategy for encapsulating bioactive compounds, improving their absorption, stability, and functionality. This study provides an exploration of the synthesis, characterization, and postharvest protection applications of nanocarriers formed through the complexation of chitosan oligomers, carboxymethylcellulose, and alginate in a 2:2:1 molar ratio. This complexation process was facilitated by methacrylic anhydride and sodium tripolyphosphate as cross-linking agents. Characterization techniques employed include transmission electron microscopy, energy-dispersive X-ray spectroscopy, infrared spectroscopy, thermal analysis, and X-ray powder diffraction. The resulting hollow nanospheres, characterized by a monodisperse distribution and a mean diameter of 114 nm, exhibited efficient encapsulation of carvacrol, with a loading capacity of approximately 20%. Their suitability for phytopathogen control was assessed in vitro against three phytopathogens—Botrytis cinerea, Penicillium expansum, and Colletotrichum coccodes—revealing minimum inhibitory concentrations ranging from 23.3 to 31.3 μg·mL⁻¹. This indicates a higher activity compared to non-encapsulated conventional fungicides. In ex situ tests for tomato (cv. ‘Daniela’) protection, higher doses (50–100 μg·mL⁻¹, depending on the pathogen) were necessary to achieve high protection. Nevertheless, these doses remained practical for real-world applicability. The advantages of safety, coupled with the potential for a multi-target mode of action, further enhance the appeal of these nanocarriers.

This article evaluates horizontal daily global solar irradiation predictive modelling using artificial neural networks (ANNs) for its application in agricultural sciences and technologies. An eight year data series (i.e., training networks period between 2004–2010, with 2011 as the validation year) was measured at an agrometeorological station located in Castile and León, Spain, owned by the irrigation advisory system SIAR. ANN models were designed and evaluated with different neuron numbers in the input and hidden layers. The only neuron used in the outlet layer was the global solar irradiation simulated the day after. Evaluated values of the input data were the horizontal daily global irradiation of the current day [H(t)] and two days before [H(t−1), H(t−2)], the day of the year [J(t)], and the daily clearness index [Kt(t)]. Validated results showed that best adjustment models are the ANN 7 model (RMSE = 3.76 MJ/(m²·d), with two inputs ([H(t), Kt(t)]) and four neurons in the hidden layer) and the ANN 4 model (RMSE = 3.75 MJ/(m²·d), with two inputs ([H(t), J(t)]) and two neurons in the hidden layer). Thus, the studied ANN models had better results compared to classic methods (CENSOLAR typical year, weighted moving mean, linear regression, Fourier and Markov analysis) and are practically easier as they need less input variables.