Environmental Applications Research Articles

A Scalable Fully Printed Organic Thermoelectric Generator for Harsh Environments Enabled by a Stable n‐type Polymer

AbstractAffordable and versatile power sources become crucial as miniaturized electronics and sensors become more widespread. Organic thermoelectric generators (TEGs), capable of tapping into wasted heat sustainably and economically, are viewed as key enablers for powering the sensor networks of the future. Until recently, the performance of n‐type organic thermoelectric materials has severely lagged behind their p‐type counterparts. However, reports of a stable and highly conductive n‐type polymer, poly(benzodifurandione) (PBFDO), are changing this notion. Nonetheless, validation of PBFDO as a suitable ink for scalable fabrication processes and integration of the material into a scalable organic TEG have yet to be demonstrated. This work presents the development, characterization, and optimization of a PBFDO ink for use in a scalable inkjet printing process. The n‐type ink is then integrated into a screen‐printed origami‐inspired architecture, resulting in a 21‐leg PEDOT:PSS/PBFDO organic TEG capable of delivering a record‐high normalized power density among reported polymer‐based TEGs of 0.718 nW cm−2 K−2. Moreover, the module ambient stability is demonstrated for up to 90 d, while its use for potential applications in harsh environments is validated for a temperature range of ‐8 °C to 200 °C and up to 90% relative humidity, a first for organic TEGs.

Multiscale textured solar absorber coatings for next-generation concentrating solar power

A high-temperature stable solar absorber is crucial for next-generation (Gen3) concentrating solar power (CSP) plants, to enable high temperature operation, maximize power generation efficiency, and thereby reduce the levelized cost of energy. This study presents novel, fractal-textured solar absorber coatings whose multiscale feature scales effectively match the visible region of the solar spectrum, leading to superb absorptive properties. Single and bimetallic oxide coatings of copper, cobalt and manganese were prepared on Inconel 625 substrates using electrodeposition. The effect of electrodeposition parameters and annealing temperature are systematically studied to optimize the morphology and properties of the oxide coatings. Multiscale textured bimetallic coatings of copper manganese oxide and copper cobalt oxide demonstrate a superior absorptance of 0.985, a remarkably low emittance <0.45 and an exceptional optical efficiency of ∼96 % under Gen3 CSP operating conditions, surpassing previously reported values in the literature by about 5 %. Durability tests confirmed the coatings’ steadfast endurance of mechanical and environmental stress, making them suitable for long-term application in harsh CSP environments.

Improved Photocatalytic Activity of Dion–Jacobson-Type Tantalate Perovskites Modified with FeCl2

A rapid and feasible approach was used to develop visible-light-driven-type Dion–Jacobson perovskites by the modification of the RbLaTa2O7 host (RbLTO) with FeCl2 through the molten salt route. X-ray diffraction (XRD) characterization showed that FeCl2-modified layered perovskite (e.g., Fe@RbLTO) preserved its lamellar structure. SEM micrographs confirmed the layered morphology of both RbLTO and Fe@RbLTO perovskite materials. The UV-Vis spectra illustrated a significant red shift of the absorption edge after Fe2+ modification, with the band gap energy reducing from 3.88 to 1.82 eV. H2-TPR measurements emphasized the anchorage of Fe2+ species located on the surface of the layered perovskite as well as in the interlayer space. The synthesized materials were valorized as photocatalysts for the degradation of phenol under both Xe lamp and simulated solar irradiation (SSL) conditions. The photocatalytic reaction follows first-order kinetics. By-product formations during phenol (Ph) degradation were identified and quantified using high-performance liquid chromatography (HPLC). Hydroquinone, 1,2-dihydroxi-benzene, benzoquinone, and pyrogallol were identified as the main Ph degradation intermediates. Pristine RbLaTa2O7 exhibited a phenol conversion value of about 17% using an Xe lamp, while a ≈ 11% conversion was achieved under SSL. A substantial increase in Ph conversion and selectivity was perceived after Fe2+ modification. Fe@RbLTO demonstrated superior photocatalytic performances (43% conversion of phenol under an Xe lamp, and 91% selectivity to aromatic intermediate compounds) at optimized reaction conditions. The stability of the Fe@RbLTO photocatalyst when exposed to an Xe lamp was also assessed. These results suggest that the existence of iron species on the layered perovskite’s surface is responsible for the improved redox properties of Fe@RbLTO, resulting in a valuable material for environmental applications.

Effect of filer content on the thermal characteristics of underfill materials for Ball-Grid-Array component package

High-density integration and fast processing speed in the semiconductor industry have increased heat generation in electronic devices. Underfill materials, known for their high thermal conductivity and low coefficient of thermal expansion (CTE), offer a potential solution to dissipate heat and improve device reliability. In this study, we investigate the effect of filler content on the thermal reliability of underfill materials for ball grid array (BGA) component packaging. Mainly, we investigate the thermal conductivity, CTE, and mechanical properties of different filler contents of Al2O3 and Al2O3–BN hybrid underfills to facilitate heat dissipation and improve device reliability. The thermal conductivity of the underfill materials was evaluated by measuring the surface temperatures of underfill molded flip-chip light-emitting diodes (FCLEDs). The mechanical properties and thermo-mechanical reliability of the underfill materials were evaluated via a three-point bending test of the underfill packaged BGA components after the thermal shock test. The results showed that optimizing underfill properties based on specific application environments is crucial for obtaining enhanced thermal reliability and mechanical properties of underfill packaged BGA components.

Intelligent CAD Modeling and Reinforcement Learning Application in Environment and Landscape Design

Intelligent CAD Modeling and Reinforcement Learning Application in Environment and Landscape Design

Designing MOF-COF hybrid materials for energy, biomedical and environment applications

Designing MOF-COF hybrid materials for energy, biomedical and environment applications

A novel green nanocomposite for EOR: Experimental Investigation of IFT Reduction, wettability Shift, and nanofluid stability

A stable nanofluid (NF) is crucial for success of nano-enhanced oil recovery (nEOR) processes. However, this represents a significant challenge as nanoparticles (NPs) tend to agglomerate under high salinity and NP concentration adversely affecting the oil recovery. New nanomaterials including functionalized nanoparticles also known as nanocomposites (NC) can help to overcome these issues. In this paper, first, we reported synthesis, characterization, and performance evaluation of a novel hydrophobic CuO-SiO2-Montmorillonite-K+-Thiazine NC for the first time. The NC was characterized using Scanning Electron Microscopy (SEM), Energy Dispersive X-Ray Analysis (EDAX), X-Ray Diffraction (XRD), Thermogravimetry Analysis (TGA), and Fourier Transform Infrared Spectroscopy (FTIR). SEM analysis showed that the NC is composed of uniformly distributed NPs. EDAX results confirmed presence of Cu, SiO2, O2, and Cl in the NC. XRD analysis indicated that SiO2 is the dominant phase in the crystal lattice and responsible for adsorption capacity of the NC. TGA analysis showed that the NC will be thermally stable in typical reservoir temperatures (∼80°C). FTIR results confirmed presence of Si-O, Cu-O, Si-O-Si, Al-O-Si, Al-OH, and OH bonds in the NC. In the second phase of this research work, the novel NC was used to investigate recovery of a Kazakhstani paraffinic heavy crude oil from Berea sandstone with focus on IFT reduction, oil recovery, wettability alteration, and stability analysis of the NFs. NFs were prepared with NC concentrations of 250, 500, and 1,000 ppm using moderate salinity (MS), low salinity (LS), and distilled water (DW). The results showed that the optimal NF (250 ppm LS) exhibited a high zeta potential value (−65.5 mV) indicating a high stability which is superior to all of the previously reported NCs. This high stability is attributed to use of thaizine as a source of natural surfactant. The optimum NF also altered the wettability of the sandstone by 77.6% and the contact angle (CA) was reduced from 117.9° to 26.4° making the system strongly water wet. The nanoclay has significantly facilitated the wettability alteration. The optimum NF also reduced the IFT by 92.3% from 27.42 mN/m to 2.11 mN/m. An incremental oil recovery of 20% was also achieved in the tertiary or EOR stage of oil. A comparison with the NCs reported in the literature confirmed the excellent performance of this novel NC in terms of NF stability, IFT reduction, and wettability alteration. The novel NC has a great potential for nEOR and other oilfield and environmental applications.

Micro-Nano Bubbles in Action: AC/TiO2 Hybrid Photocatalysts for Efficient Organic Pollutant Degradation and Antibacterial Activity

Developing highly active and sustainable photocatalysts is crucial for environmental remediation. This work focuses on the enhanced photocatalytic degradation efficiency of synthetic dyes using TiO2-coated AC hybrid photocatalysts under MNB aeration. The TiO2-coated AC hybrid photocatalyst (HP) was synthesized via a sol-gel method and characterized using XRD, FTIR, SEM, EDS, HR-TEM, and DRS. The study investigated the photocatalytic degradation of three dyes indigo carmine (IC), reactive black 5 (RB5), and methylene blue (MB) in wastewater, with initial dye concentrations ranging from 10 to 100 μM. Under UVA irradiation, the hybrid photocatalyst with MNB aeration (HP+UVA+MNB) achieved the highest degradation efficiencies of 69.09%, 60.06%, and 55.19% for IC, MB, and RB5, respectively. Further analysis showed that the chromophores and complex structures of these dyes were broken into intermediate products. The Langmuir-Hinshelwood kinetic model was used to describe the reaction mechanisms. The HP+UVA+MNB system demonstrated superior photocatalytic degradation activity, making it suitable for operational and environmental applications in dye wastewater treatment. Additionally, the antibacterial properties of AC and HP were tested at 100 μg/mL, showing effectiveness against both Gram-positive Staphylococcus aureus and Gram-negative Escherichia coli.

Process Development of a Liquid-Gated Graphene Field-Effect Transistor Gas Sensor for Applications in Smart Agriculture

A compact, multi-channel ionic liquid-gated graphene field-effect transistor (FET) has been proposed and developed in our work for on-field continuous monitoring of nitrate nitrogen and other nitrogen fertilizers to achieve sustainable and efficient farming practices in agriculture. However, fabricating graphene FETs with easy filling of ionic liquids, minimal graphene defects, and high process yields remains challenging, given the sensitivity of these devices to processing conditions and environmental factors. In this work, two approaches for the fabrication of our graphene FETs were presented, evaluated, and compared for high yields and easy filling of ionic liquids. The process difficulties, major obstacles, and improvements are discussed herein in detail. Both devices, those fabricated using a 3 μm-thick CYTOP® layer for position restriction and volume control of the ionic liquid and those using a ~20 nm-thick photosensitive hydrophobic layer for the same purpose, exhibited typical FET characteristics and were applicable to various application environments. The research findings and experiences presented in this paper will provide important references to related societies for the design, fabrication, and application of liquid-gated graphene FETs.

Chemiresistive triethylamine detection based on the novel Ti3C2Tx/Co-BDC gas sensor

Triethylamine (TEA), a representative volatile organic environmental pollutant, poses significant environmental pollution risks and can adversely affect the liver and nervous system, potentially leading to fatal outcomes. However, existing gas sensors for TEA detection have pressing drawbacks, such as safety hazards associated with high-temperature operation and poor timeliness due to time-consuming testing. Herein, the Ti3C2Tx/Co-BDC sensor demonstrates ultra-sensitive detection of TEA at a low temperature of 100 °C. This temperature is below the threshold for explosion-proof operation, ensuring safe application in flammable and explosive environments. Meanwhile, the introduction of the metal-like MXene with ultra-high conductivity accelerates the response and recovery process (11s/20s), facilitating highly efficient TEA detection within a sub-minute timeframe. The Ti-O-Co interfacial bonds between Ti3C2Tx and Co-BDC, confirmed by both XPS analysis and theoretical calculations, enhance carrier mobility across the two materials, significantly boosting gas-sensing performance. The rapid detection of TEA at low temperatures makes the Ti3C2Tx/Co-BDC sensor more suitable for practical environmental monitoring in flammable and explosive areas, further contributing to human health and production safety.

Filtration compatibility of clay-nonwoven geotextiles under normal stress

Nonwoven geotextiles are commonly utilized as filter materials in drainage and filtration engineering. This study focuses on the clogging phenomenon of the nonwoven geotextile filter wrapping the blind drain in the active anti-floating technology of underground structures. In this paper, the filtration compatibility of clay-nonwoven geotextiles was evaluated using a newly developed gradient ratio test device that can apply normal stress. Two fabrication technics and four specifications of nonwoven geotextiles were used to filter clay, and the geotextiles’ clogging degree was assessed after the test. The influences of normal stresses, hydraulic gradients, and fabrication technics on nonwoven geotextile filtration performance were discussed based on results from a series of gradient ratio tests. Relevant assessment parameters (clogging coefficient, soil retention, and equivalent porosity) were also presented to quantify the clogging degree of nonwoven geotextiles after the test. Furthermore, the clogging process of nonwoven geotextiles filtering clay was initially explored, and the filtration effect of the needle-punched and heat-bonded nonwoven geotextiles was evaluated. The results showed that normal stress had a significant effect on nonwoven geotextile filtration, with needle-punched nonwoven geotextiles having better soil filtration and water permeability. Discussions on nonwoven geotextile applications in specific environments or conditions are also presented.

Short DNAzymes for Efficient Catalysis of "Click" Reactions in Solution and on Surface.

We have systematically investigated and found surprising superior catalytic activities of very short DNAzymes for copper(I)-catalyzed azide-alkyne cycloaddition (CuAAC), both in solution and on surface. As a key reaction of the "click chemistry" class, CuAAC is a highly efficient and specific covalent conjugation tool with demonstrated applications in organic synthesis, bioconjugation, and surface functionalization; however, it requires the presence of the Cu(I) catalyst, which is an unstable species in aqueous solutions. We show here that one ultrashort, 14-nucleotide-truncated fragment of an earlier in vitro selected DNAzyme (CLICK-17) shows a striking and superior catalytic activity toward the in trans CuAAC reaction in solution and on surface in the presence of either Cu(I) or Cu(II), at significantly lowered concentrations. These results obviate the need for long-sequence DNAzymes, selected out of the homogeneous solution phase, for application in complex surface environments.

Beyond the lab: feasibility of cognitive neuroscience data collection during a speleological expedition

In human cognitive neuroscience and neuropsychology studies, laboratory-based research tasks have been important to establish principles of brain function and its relationship to behaviour; however, they differ greatly from real-life experiences. Several elements of real-life situations that impact human performance, such as stressors, are difficult or impossible to replicate in the laboratory. Expeditions offer unique possibilities for studying human cognition in complex environments that can transfer to other situations with similar features. For example, as caves share several of the physical and psychological challenges of safety-critical environments such as spaceflight, underground expeditions have been developed as an analogue for astronaut training purposes, suggesting that they might also be suitable for studying aspects of behaviour and cognition that cannot be fully examined under laboratory conditions. While a large range of topics and tools have been proposed for application in such environments, few have been used in the field. Methods and procedures for maximizing the robustness and scientific value of expedition research designs must first be developed and validated. We tested the feasibility of collecting human physiological, cognitive, and subjective experience data concerning brain state, sleep, cognitive workload, and fatigue, during a speleological expedition in a remote region. We document our approaches and challenges experienced, and provide recommendations and suggestions to aid future work. The data support the idea that cave expeditions are relevant naturalistic paradigms that offer unique possibilities for cognitive neuroscience to complement laboratory work and help improve human performance and safety in operational environments.

An Improved Hyper Spectral Imaging for Accurate Disease Diagnosis in Sustainable Medical Environments

Hyper spectral imaging (HSI) has emerged as a powerful technique for accurate disease diagnosis in medical environments. It provides high-resolution images with detailed spectral information, making it possible to identify subtle differences between healthy and diseased tissues. However, current HSI systems face challenges in terms of accuracy and efficiency, limiting their widespread application in sustainable medical environments. To overcome these challenges, our team has developed an improved HSI system that utilizes state-of-the-art spectral imaging technology and machine learning algorithms. This system is capable of capturing and analyzing a wider range of spectral data, enabling more precise identification of disease-specific spectral signatures. Furthermore, our system has been optimized to operate with minimal power consumption, making it environmentally friendly and suitable for sustainable medical environments. The improved HSI system has been successfully tested in clinical settings and has shown promising results in accurately diagnosing various diseases such as cancer, dermatitis, and cardiovascular conditions. Its high accuracy and fast processing time make it a valuable tool for early disease detection and treatment planning. Moreover, the ability to operate with low energy consumption makes it a sustainable solution for medical facilities in resourcelimited areas. In addition to its accuracy and efficiency, our improved HSI system is also user-friendly and can be easily integrated into existing medical imaging systems.

LightDPH: Lightweight Dual-Projection-Head Hierarchical Contrastive Learning for Skin Lesion Classification

AbstractEffective skin cancer detection is crucial for early intervention and improved treatment outcomes. Previous studies have primarily focused on enhancing the performance of skin lesion classification models. However, there is a growing need to consider the practical requirements of real-world scenarios, such as portable applications that require lightweight models embedded in devices. Therefore, this study aims to propose a novel method that can address the major-type misclassification problem with a lightweight model. This study proposes an innovative Lightweight Dual Projection-Head Hierarchical contrastive learning (LightDPH) method. We introduce a dual projection-head mechanism to a contrastive learning framework. This mechanism is utilized to train a model with our proposed multi-level contrastive loss (MultiCon Loss), which can effectively learn hierarchical information from samples. Meanwhile, we present a distance-based weight (DBW) function to adjust losses based on hierarchical levels. This unique combination of MultiCon Loss and DBW function in LightDPH tackles the problem of major-type misclassification with lightweight models and enhances the model’s sensitivity in skin lesion classification. The experimental results demonstrate that LightDPH significantly reduces the number of parameters by 52.6% and computational complexity by 29.9% in GFLOPs while maintaining high classification performance comparable to state-of-the-art methods. This study also presented a novel evaluation metric, model efficiency score (MES), to evaluate the cost-effectiveness of models with scaling and classification performance. The proposed LightDPH effectively mitigates major-type misclassification and works in a resource-efficient manner, making it highly suitable for clinical applications in resource-constrained environments. To the best of our knowledge, this is the first work that develops an effective lightweight hierarchical classification model for skin lesion detection.

Sensor response and radiation damage effects for 3D pixels in the ATLAS IBL Detector

Pixel sensors in 3D technology equip the outer ends of the staves of the Insertable B Layer (IBL), the innermost layer of the ATLAS Pixel Detector, which was installed before the start of LHC Run 2 in 2015. 3D pixel sensors are expected to exhibit more tolerance to radiation damage and are the technology of choice for the innermost layer in the ATLAS tracker upgrade for the HL-LHC programme. While the LHC has delivered an integrated luminosity of ≃ 235 fb-1 since the start of Run 2, the 3D sensors have received a non-ionising energy deposition corresponding to a fluence of ≃ 8.5 × 1014 1 MeV neutron-equivalent cm-2 averaged over the sensor area. This paper presents results of measurements of the 3D pixel sensors' response during Run 2 and the first two years of Run 3, with predictions of its evolution until the end of Run 3 in 2025. Data are compared with radiation damage simulations, based on detailed maps of the electric field in the Si substrate, at various fluence levels and bias voltage values. These results illustrate the potential of 3D technology for pixel applications in high-radiation environments.

THE ROLE OF GEOSPATIAL ARTIFICIAL INTELLIGENCE (GEOAI) IN SMART BUILT ENVIRONMENT MAPPING: AUTOMATIC OBJECT DETECTION OF RASTER TOPOGRAPHIC MAPS IN MALAYSIA

Smart built environment mapping is integrating Geospatial Artificial Intelligence (GeoAI) to enable advanced analysis, pattern recognition, and decision-making processes. This shift in understanding, planning, designing, and managing the built environment is paving the way for a smarter, more sustainable future. This commentary explores the current role of AI in enhancing technology use within the geospatial field, focusing specifically on the application of GeoAI in mapping the built environment. Additionally, the paper presents a selection of case studies related to the implementation of AI in developing automatic vectorization, particularly for geospatial mapping in built environments. This research demonstrates the effectiveness of using Convolutional Neural Network (CNN) models for sorting objects in scanned, old topographic maps of the built environment. The findings of this study are valuable for making informed decisions, devising effective strategies, and identifying opportunities for further research and exploration within the dynamic field of GeoAI in smart built environment mapping and applications.

Bioplastic films from starch of Colocasia esculenta and its waste: A smart template for sensing applications

The over usage plastics have possessed serious threat to the ecological system. Thus progressive advancement in fabricating biodegradable and renewable bioplastics is persuasively required to furnish an effective alternative to non-biodegradable plastics. In this view, the current work highlights the production of starch based bioplastic films using waste Colocasia esculenta (taro herb) as a viable starting precursor. The functional ability of developed taro starch based film was further modified by incorporating carbon dots (CQDs) fillers generated from the waste slurry produced during starch extraction from taro herbs. The optimization of films production was achieved by varying the CQDs amount (0.4 %, 0.8 %, 2 % and 4 % w/w) on taro-based films using casting technology. The data illustrates that the addition of CQDs has the ability to enhance the fluorescence property, mechanical properties (Tensile Strength 0.332–4.635 MPa, Elongation at break 42.45–547.63 %) and water resistance ability of films (Moisture content 15–6.4 %, Water Solubility 50–30 % Water Vapour Transmission Rate 2.0012–1.0054 g−2 h−1 and Water Contact Angle 40.6–89.6°). The developed films are found to be thermally stable. The formed films possessed anti-oxidative abilities which safeguard the film from oxidative attacks and ultimately protect the film from the external environment. The fluorescence nanosensor probe has further been developed by utilizing CQDs embedded in a starch-based bioplastic nanocomposite. The developed sensor displayed selective sensing ability towards Fe2+ ion with high sensitivity and accuracy in aqueous medium. Thus, the proposed sensor in this work offers a portable, efficient, low-cost, disposable, non-lethal, and eco-friendly nanosensor for on-site monitoring of metal ion for the food, beverage, and pharmaceutical industries. This is one of the primary reports where metal ions sensing is reported for Taro@CQDs nanocomposites based films. Our outcomes of this work hold significant relevance to providing a smart sensory and biodegradable probe for metal ion sensing by using waste resources, thus offering a better and sustainable alternative for environmental remediation applications.

The effect of non-perpendicular incidence angles on discharge characteristics in an argon atmospheric plasma jet impinging on metal, water and glass substrates

The spatial–temporal discharge behavior of an AC argon plasma jet tilted at non-perpendicular incidence angles (60°, 45°, and 30°) interacting with an ungrounded metal, water, and glass plate placed on the jet propagation track was studied by the fast-imaging technique. The conductivity of surface and incidence angles plays an essential role in the discharge current and dynamic process of the plasma jet. The nearly consistent time delay between subsequent breakdowns occurred four times for metal and two times for glass treatments. The mean luminous intensity of the plasma in one discharge cycle at the discharge area between ground electrode and target surface region for the water and glass case decreased by 39.5% and 20.5% when the incidence angle decreased from 60° to 30°, respectively. In particular, the incidence angle and gas flow rate notably impacted the spatial extension behavior created on the glass surface but had no significant difference in discharge characteristic of plasma jet with metal case. In addition, two equivalent circuit models were developed based on the simulation of the micro-discharges and the geometry of the “plasma jet–substrate” system, respectively. These results will obtain further insight into the underlying mechanisms of plasma-target interaction and facilitate the designing of appropriate jet for environmental and biomedical applications.

Environmentally Friendly Synthesis of Gelatin Hydrogel Nanoparticles for Gastric Cancer Treatment, Bisphenol A Sensing and Nursing Applications: Fabrication, Characterization and ANN Modeling

This study presents a dual application approach for the environmentally friendly synthesis of gelatin hydrogel nanoparticles with potential applications in gastric cancer treatment, bisphenol A (BPA) sensing, and nursing. Gelatin hydrogel nanoparticles were synthesized using a green and freeze-drying method, avoiding the use of toxic chemicals and solvents. The nanoparticles showed excellent biocompatibility and promising potential for drug delivery system (DDS) in gastric cancer treatment. The controlled release of anticancer drugs from the gelatin nanoparticles was showed, highlighting their potential in targeted therapy. Additionally, the gelatin hydrogel nanoparticles were explored for BPA sensing. BPA is a widely used chemical known for its adverse effects on human health. The gelatin nanoparticles showed high selectivity and sensitivity towards BPA detection, making them suitable for environmental monitoring and health applications using scanning electron microscope (SEM). Also, in this study, an artificial neural network (ANN) was used to estimate the release of docetaxel (%) at 72 hours, the release of paclitaxel (%) at 72 hours, tensile strength with sample (wt%), and porosity (%) in broader ranges than the experimental samples. The environmentally friendly synthesis of gelatin hydrogel nanoparticles presented in this study offers a versatile platform with dual applications in gastric cancer treatment and sensing of harmful chemicals. The obtained results show the potential of these nanoparticles for innovative therapeutic and diagnostic strategies in healthcare and environmental monitoring. The study showed the development of sustainable and multifunctional nanomaterials for various biomedical applications. The modeling of the neural network predictions shows that increasing the sample (wt%) and porosity (%) leads to an increase in the release of docetaxel (%) at 72 hours, the release of paclitaxel (%) at 72 hours, and tensile strength. As porosity decreases, the release of docetaxel increases, and the release of paclitaxel and tensile strength also increase. Additionally, the prediction errors of the ANN in this study were evaluated using linear regression, showing acceptable error rates compared to the target results obtained from the experimental tests.