Precise regulation of carbon dioxide (CO 2 ) concentrations in plant growth chambers is critical for ensuring reproducible and physiologically relevant research outcomes. CO 2 assimilation varies significantly with plant genotype, growth conditions, crop density, and phenological stage. However, estimation and control approaches heavily dependent on mechanistic crop models are at odds with the objectives of plant characterization units (PCU), where model availability for specific crops may be lacking. Moreover, in Bioregenerative Life Support Systems (BLSSs), such methods may struggle with multiple crops, intercropping, staggered harvesting and unknown growth stages. We propose a real-time, crop-agnostic method to estimate photosynthetic and respiration rates from CO 2 concentration data, without relying on crop-specific mechanistic assumptions. This improves robustness against the time-varying conditions typical of BLSSs, and supports operation with crops lacking validated physiological models. The resulting rate estimates support diagnostic algorithms, supervisory logic and CO 2 concentration controllers, and provide the modeling foundation for our second contribution: a hybrid Model Predictive Control (MPC) strategy for CO 2 regulation. The controller employs a mixed-integer formulation to handle the disjoint operating ranges of injection valves and incorporates explicit compensation for CO 2 measurement delays, ensuring accurate mass balances under real operating conditions. We demonstrate the effectiveness of the approach through in vivo experiments in a PCU realized under the ESA-MELiSSA framework. • Real-time observer for estimating photosynthesis and respiration rates. • Hybrid Model Predictive Control to ensure highly precise CO 2 regulation. • Robustness to intercropping, staggered harvesting and unknown growth stages. • Control formulation favoring integration in Bioregenerative Life Support Systems. • Validation through in vivo experiments in a Plant Characterization Unit.

Occurrence, distribution and ecological risk assessment of soil pesticide residues in cotton areas of Xinjiang.

Phosphorus (P) availability is a critical factor influencing plant growth, particularly in highly weathered tropical and subtropical soils where mineral and organic P sources often exhibit low absorption efficiency. In response to soil low P availability, plants typically undergo physiological and biochemical adaptation, including reduced photosynthetic rates, increased root/shoot ratio, and alterations in the root system. This study aimed to assess changes in the maize root system and their relationship with P absorption and utilization efficiency under field conditions. The experimental design comprised three treatments: pig slurry, mineral fertilizer, and a control with no fertilizer, arranged in a randomized block design with four replications. Key morphological parameters were analyzed at the vegetative (V8) and flowering (R1) phenological stages, alongside physiological and chemical assessments of the aboveground plant parts. Plants grown in soil with a history of pig slurry application had the lowest morphological root parameters, yet demonstrated higher P absorption efficiency, grain yield, and dry matter production. The application of pig slurry and mineral fertilizers increased P and potassium (K) levels in the soil, photosynthetic rates, and dry matter production. These findings underscore the complex interplay between root morphology and nutrient absorption, offering insights into optimizing fertilizer strategies for maize cultivation in low-P availability soils.

The wine industry in the Bordeaux region of southwestern France is globally recognized for producing premium wines derived primarily from Vitis vinifera cultivars such as Cabernet Sauvignon, Merlot, and Cabernet Franc. The success of Bordeaux wines is closely linked to grapevine phenology, grape composition, and winemaking practices. Grapevine phenology refers to the seasonal growth stages of the vine, including budburst, flowering, veraison, and harvest, which are strongly influenced by climatic conditions. These stages determine berry development and ultimately influence the chemical composition of grapes, including sugar levels, acidity, phenolics, and aromatic compounds that shape wine quality. Climate variability and vineyard management practices significantly affect these processes in Bordeaux vineyards. This study presents comprehensive guidelines and care practices related to grapevine phenology, grape composition, and wine production, with a focus on maintaining high wine quality in Bordeaux. The article also examines the impact of environmental conditions, vineyard management strategies, and winemaking techniques on grape development and wine characteristics. The findings emphasize that understanding phenological stages and grape composition is essential for optimizing vineyard management, adapting to climate change, and ensuring consistent wine quality.

Dalbulus maidis is a key pest and vector of maize pathogens in Latin America. Understanding the field population dynamics of D. maidis is essential for improving management strategies and reducing the risk of pathogen transmission in maize. This study evaluated the population density and stage structure of D. maidis across maize vegetative stages and determined the effects of crop development and climatic variables on the abundance of eggs, nymphs, and adults over three growing seasons. Field trials were conducted over three consecutive second-crop seasons (2022-2024) in six commercial maize fields in Jataí, Goiás, Brazil. Insect densities (eggs, nymphs, and adults) were monitored every three days using direct plant inspections, and meteorological data were recorded. Insect populations were assessed from V2 to VT stages, and the effects of plant age, phenological stage, and climatic variables were analyzed using multiple regression models. Results showed that D. maidis egg and adult densities were higher than nymph densities across all seasons. A consistent pattern was observed wherein early maize stages (V2-V4) favoured oviposition and nymphal development, while adults predominated in later stages (V5-VT). There was a positive and significant correlation between adult density and the age and phenological stage of the plants, while eggs and nymphs did not show a significant correlation with age, phenological stage, or climatic variables. These findings have important implications for Integrated Pest Management(IPM), highlighting a critical window early in crop development when monitoring and control actions are likely to be most effective for preventing population buildup and subsequent pathogen transmission.

The piercing-sucking insects present in different crops cause physiological and morphological changes during vegetative development and flowering. However, more knowledge is needed about whether plant mechanisms are affected by stink bug injury, especially that imposed by nymphs and male or female adults. Furthermore, the feeding time of piercing-sucking insects can significantly alter crop damage. This study was conducted to determine the damage caused by different life stages (nymphs and adults) and by different sexes of Tibraca limbativentris in two rice plant phenological stages. The development and yield were evaluated following the infestation of nymphs and adults of different sexes in the vegetative and reproductive stages of rice plants. In addition, the development, yield, and gas exchange of rice plants infested under different nymph densities in the vegetative and reproductive stages were evaluated. We did not find any consistent relationship between the number of nymphs and rice yield. T. limbativentris nymphs did not cause losses to grain yield on rice in this study (in both experiments). However, the nymphs caused a significant increase in the number of stalks exhibiting dead heart symptoms, showing results similar to the adult insects. Nymph feeding affected photosynthetic processes in rice leaves only when infestations happened at the vegetative stage. Stomatal conductance was also affected when infestations occurred at the reproductive stage. Further studies are critical to understand the mechanisms underlying the injury and to evaluate the potential damage of nymphs under field conditions. The impact caused by the combination of nymphs and adults in the field must be evaluated.

Exploring the effect of phenological stage, plant part and drying on oil quantity and quality of a new Indian variety of Oregano vulgare var. CIM-Sudeeksha under agroclimate of Uttarakhand foothills

Spring frost poses a major threat to apple production in temperate regions, with severe implications for yield and fruit quality. China's apple production is particularly vulnerable to spring low temperature, yet comprehensive assessments of apple spring frost-induced production losses remain limited. In this study, we quantified frost-induced apple yield and production losses across China during 1991-2020 by integrating spring frost characteristics and simulated production losses. Frost hazard was characterized using the frequency (accumulated frost days, AFD) and intensity (accumulated frost degree-days, AFDD) of frost events occurring during frost-sensitive phenological stages of apple. Yield losses caused by frost were simulated using the process-based STICS model while spatial exposure was represented by the distribution of apple harvested regions derived from the Spatial Production Allocation Model (SPAM). Total apple production loss was estimated based on simulated yield, yield loss rate, and harvested region. The results show that the average annual AFD ranged from 0.04 to 1.20 d, while AFDD varied between 0.03 and 0.80°C·d across major apple-planting regions. Frost events resulted in measurable yield reductions, with an average yield loss of 1.3%, and a maximum loss of 9.5% occurring in Region III. During the past three decades, spring frost-induced yield loss rates generally showed an increasing trend, particularly in the Loess Plateau.When combined with the spatial distribution of apple planting regions (averaging 760.7ha), the estimated national average production loss reached 245.4 t. This study provides a quantitative assessment of frost impacts on apple production at the national scale and offers valuable insights for improving frost risk management, optimizing orchard distribution, and enhancing the resilience of apple production under increasing climate variability.

Sunflower [Helianthus annuus L. (Asteraceae)] is a crop of considerable significance in agricultural production. This study was conducted during the 2023 growing season in Tokat Province to identify harmful Lepidoptera species associated with sunflower and their natural enemies. Preimaginal stages were periodically collected from sunflower fields at various phenological stages of the plant. These specimens were then reared under controlled laboratory conditions (25±2°C and 60±5% relative humidity) in containers containing sunflower leaves, and their development was monitored. The emerged adult Lepidoptera and parasitoids were subsequently identified. Taxonomic diagnoses revealed that the lepidopteran species was Plutella xylostella (Lepidoptera: Plutellidae), and its associated parasitoid was Diadromus subtilicornis (Hymenoptera: Ichneumonidae). Based on these findings, sunflower was recorded as a new host plant for P. xylostella. Furthermore, P. xylostella was documented as a new faunistic record for Tokat Province. Additional information is provided regarding the host range, geographic distribution in Turkey and globally, and known parasitoids of P. xylostella.

Prodiplosis longifila (Diptera: Cecidomyiidae) has recently emerged as a major threat in foliage production systems in Colombia; however, key aspects of its damage, population dynamics, and monitoring remain poorly understood. This study addresses these knowledge gaps by evaluating phenological stages, injury patterns, economic impact, and spatio-temporal population dynamics of P. longifila in the foliage crops Ruscus aculeatus and Cocculus laurifolius under open-field and greenhouse conditions in commercial production areas. Monitoring efficiency was assessed using traps of different colors and heights to optimize sampling protocols and improve understanding of adult behavior. Field data were complemented with spatio-temporal analyses to characterize dispersal patterns and aggregation processes within production systems. Damage was detected across all three larval instars, with the most severe injury occurring during the first and second instars, resulting in significant reductions in foliage quality and marketability. Productivity losses reached 53% in R. aculeatus and 29% in C. laurifolius, accompanied by sharp declines in extra-quality stems and maximum income losses of 79% and 56%, respectively. Adults exhibited a consistent preference for black, white, and yellow traps placed 10-30cm above host plants, providing practical guidelines for improving monitoring accuracy. Kernel density analyses revealed that populations initially aggregated along greenhouse borders and subsequently dispersed toward the interior, generating internal hotspots associated with localized environmental and microclimatic conditions. Adult activity was predominantly crepuscular, with clear peaks between 21:00-22:00h and 03:00-04:00h. This study provides the first integrated assessment of P. longifila in foliage crops, generating critical ecological and applied information to support improved monitoring, early detection, and targeted management strategies for this emerging pest in ornamental foliage production systems.

Double-cropping grape systems offer enhanced land productivity but face significant challenges from climate variability, particularly rain stress and pest outbreaks during critical phenological stages. Accurate phenological prediction is essential to synchronize management practices with crop development and improve ecological resilience. This study presents a novel deep learning framework that integrates MobileNet with an augmented version of Dream Optimizer [Augmented Dream Optimizer (ADO)] to model grape phenology using satellite-derived time series of Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and rainfall from the CropHarvest dataset. The model transforms temporal data into pseudo-images for efficient spatiotemporal feature extraction, achieving 93% classification accuracy and a 6.1-day mean absolute error in stage prediction. ADO enhances convergence and generalization by optimizing key hyperparameters through a hybrid metaheuristic search. The system further identifies high-risk periods for rain damage and pest infestation, enabling proactive interventions. The model statistically significantly outperforms machine learning and deep learning baselines (p< 0.01) across three different agroecological zones [Mediterranean (California, USA, and southern Europe), subtropical (South Australia), and temperate (central Europe)] through spatially stratified fivefold cross-validation on 3,000 held-out test samples of the CropHarvest dataset. This work demonstrates the potential of optimized lightweight neural networks in sustainable viticulture, providing a scalable tool for precision management in climate-resilient double-cropping systems.

Abstract The increasing water scarcity and rising irrigation costs in semi-arid regions like Mendoza, Argentina, threaten the sustainability of high-density walnut orchards, requiring irrigation strategies that balance yield with water productivity. This study assessed the effects of four irrigation treatments on vegetative growth, yield, and nut quality of the ‘Chandler’ cultivar over three consecutive seasons (2022–2025). Treatments consisted of: (i) full irrigation replacing 100% of crop evapotranspiration throughout the season (T100); (ii) sustained deficit irrigation at 75% ETc (T75); (iii) over-irrigation at 125% ETc (T125); and (iv) a regulated deficit irrigation strategy applying 50% ETc during spring followed by full irrigation thereafter (T50/100). The experiment was arranged in a randomized complete block design with four replicates per treatment, and data were analyzed using analysis of variance followed by LSD’s test for mean comparisons. Results indicated that T125 and T100 treatments (125 and 100% ETc, respectively) maximized yield, maintaining stem water potential (SWP) around -6 bar throughout the growing season. These treatments produced heavier and bigger nuts than deficit irrigation treatments. Over-irrigation (T125) did not significantly enhance yield or nut quality compared to T100 and resulted in lower agronomic water productivity. In contrast, moderate (T75) and spring-regulated (T50/100) deficit irrigation significantly reduced yield by 25% and 29%, respectively, also limited trunk vegetative growth and reduced kernel size and weight, although kernel color remained unaffected. While the T50/100 strategy caused a sharp decline in stem water potential during spring, recovery was rapid once full irrigation resumed. Nevertheless, the temporary reduction in growth and yield highlights the high sensitivity of walnut trees to water stress during early phenological stages. Overall, this study provides novel multi-season evidence that full irrigation at 100% ETc optimizes the trade-off between yield and agronomic water productivity, offering practical guidance for irrigation management in walnut orchards grown under semi-arid environments with limited winter rainfall and spring high atmospheric demand.

Aerial potato stem soft rot is an emerging disease in Sinaloa, Mexico, that occurs during the fall– winter season in fields watered by sprinkling irrigation systems, which create prolonged leaf wetness periods ranging from 12 to 18 h when the temperature varies from 18–29°C. The initial disease symptoms occur at the bulking stage, and the incidence reaches up to 10% with maceration of the stems. Multigene phylogenetic analysis and biochemical tests were used to identify the bacterium associated with the disease as Pectobacterium polaris. The pathogenicity of two strains of this bacterium was determined in potato, lettuce, cauliflower, orange habanero pepper, tomato, carrot, zucchini squash and garden bean plants under greenhouse conditions, as well as in detached tubers and tomato fruit, zucchini squash, carrot taproots, garden bean pods and onion bulbs in the laboratory, suggesting that the bacterium has the potential to attack these vegetable crops grown in Sinaloa. This is the first report of P. polaris causing aerial stem soft rot of potato in Mexico. This study identifies a significant new threat to vegetable production in the region, highlighting the need for future research on disease management strategies, which should address the phenological stage in which potato exhibits the highest susceptibility to the pathogen, and the climatic conditions that favour disease incidence. This will contribute to the control of the disease, to the benefit of potato growers.

ABSTRACT This study revealed that among climatic factors, rainfall, temperature, and relative humidity significantly affected the seasonal population of fall armyworm (FAW). The drier weather favoured its movement and spread whereas rainy weather with higher humidity reduced adults' foraging and larval activity. The seasonal fluctuations of population showed peaks during specific time periods corresponding to specific crop stage of maize. The damage scores, alone, were insufficient indicators for assessing maize yield losses by FAW, as plant damage and FAW infestation varied across the growth stages of maize. Moreover, variable cropping seasons and weather conditions (rainy or dry) across ecological zones significantly influenced the developmental duration of both maize and FAW. Accumulated growing degree days (GDDs) in combination with crop phenological stages proved to be effective tools for predicting FAW occurrence, infestation severity, and optimal timing for management interventions. Although temperature showed a strong association with GDDs accumulation of both maize crop and FAW, deviations from optimal thermal conditions resulted in non‐linear responses in crop development and FAW activity. Hence, suggesting a regular monitoring of crop regarding FAW incidence in relation to GDDs and crop phenology. Overall, these findings highlighted that the vegetative phase of maize, especially at 4–6 leaf stages, were found very critical for FAW damage, underscoring the utmost important time window to manage FAW effectively. Moreover, integrated consideration of climatic factors, crop phenology, and thermal requirements (GDDs) is essential for effective and predictive management of fall armyworm in maize cropping systems.

This study evaluated the susceptibility of common bean (Phaseolus vulgaris L.) cultivars to Euschistus heros feeding across various phenological stages. Three cultivars (IPR Curió, IPR Sabiá, and IPR Urutau) were infested with 0.5 insects per plant for eight days starting at anthesis and 8, 16, 24, 32, and 40 days after flowering (DAF) using a randomized block design with five replicates. E. heros did not significantly impact grain yield or reproductive abscission, except for the IPR Curió cultivar during flowering, which demonstrated substantial qualitative damage. Feeding injury resulted in increased grain punctures and the grading of commercial classification to Type 2. The most critical susceptibility period occurred during the grain-filling stages (16-24 DAF). IPR Curió was the most sensitive cultivar, exhibiting Type 2 status at both 16 and 24 DAF. These findings demonstrate that although common beans exhibit quantitative tolerance to E. heros at the tested density, qualitative damage during grain development significantly compromises marketability and value. Integrated Pest Management (IPM) should prioritize protecting the crop during mid-to-late reproductive stages to ensure that grain quality standards are met.

Transcriptomic analyses carried out on buds at different positions and developmental stages reveal the functional domains mainly involved in determining bud fertility in grapevine, with a focus on hormone signalling and floral integrators. Bud fruitfulness in grapevine (Vitis vinifera L.) depends on complex interactions between developmental stage, node position and hormonal regulation. In this study, transcriptomic analyses were performed on buds of cv. Merlot collected at three phenological stages (BBCH63, BBCH77 and BBCH90) from three node positions (2, 5 and 10), representing basal, intermediate and apical fertility patterns. RNA-Seq data revealed that phenological stage was the primary driver of transcriptional variation, while node position contributed to intra-stage differences. BBCH77 emerged as the most transcriptionally dynamic phase. Differential expression, enrichment analyses and WGCNA highlighted distinct developmental trajectories among nodes. Buds at node 5, characterized by lower fertility, showed transcriptional signatures associated with enhanced gibberellin biosynthesis and signalling, early activation of dormancy-related pathways, and complex hormonal interplay involving ethylene. In contrast, buds at node 10 displayed transcriptional features consistent with sustained auxin flux from the shoot apical meristem and reduced local inhibitory signalling, potentially supporting higher fertility. Cytokinin-related genes showed stage-dependent activation, particularly at BBCH77, suggesting a transient promotive role during floral transition. Expression profiling of flowering-related genes confirmed stage-dependent regulation of major floral integrators and revealed position-specific modulation of key regulators. Overall, the integration of positional and temporal transcriptomics supports a working model in which bud fertility results from the dynamic balance between stimulatory (auxin, cytokinins) and inhibitory (gibberellins, ethylene, ABA) signals, modulated by developmental stage and meristem proximity.

The soilless culture technique, widely used for vegetables and ornamentals, has also proven advantageous for grapevine cultivation under protected conditions. This study investigated the effects of foliar applications of different organic compounds diethylenetriaminepentaacetic acid (DTPA), ethylenediaminetetraacetic acid (EDTA), amino acids, humic acid, and fulvic acid on yield, fruit quality, and plant nutrition in soilless table grape production under greenhouse conditions in Çukurova, a warm Mediterranean region in 2021 and 2022 years. Four-year-old cv. Black Magic ( Vitis vinifera L . ) grapevines were grown under plastic cover in a pumice:cocopeat (1:1, v/v) substrate and irrigated with modified Hoagland nutrient solution. Organic substances were applied foliar at a concentration of 0.2% at three phenological stages (pre-flowering, fruit set, and veraison). The application concentration and phenological timing were chosen to coincide with critical stages of grapevine development and to maximize foliar uptake efficiency without inducing phytotoxicity. Control vines were sprayed with water only. Humic acid application increased yield by approximately 10–18% compared to the control in two growing seasons and also improved cluster weight, length, and size. Based on mean values, humic acid application increased berry weight by approximately 3–7% compared to the control across the two growing seasons. Significant treatment effects on must quality were observed mainly in the first growing season, in which amino acid and humic acid applications improved total soluble solids and maturity index compared to the control. Humic and fulvic acids enhanced leaf macro and micro nutrient concentrations by 15–35%, several nutrients into sufficient range during veraison. Humic acid and EDTA increased stomatal length by up to 45% and reduced stomatal density by approximately 15% compared to the control. Humic acid increased ascorbic acid content by approximately 150–170% and enhanced DPPH antioxidant activity by up to 8%. Fulvic acid increased total phenolic content by approximately 10–20% compared to the control.

Accurate monitoring of nitrogen (N) status is critical for precision N management and optimizing the yield and quality of Zanthoxylum armatum var. novemfolius (ZA). However, individual sensors often struggle to simultaneously capture the biochemical variations and complex canopy structural changes of ZA. Therefore, field experiments were conducted over two consecutive years, applying four N-application rates (0, 150, 300, and 450 kg N ha-1) to ZA. At each phenological stage, hyperspectral imagery and LiDAR point clouds were collected via three UAV flight altitudes (60 m, 80 m, and 100 m), and canopy nitrogen concentration (CNC) and aboveground nitrogen accumulation (AGNA) were measured. This study developed a framework by synergistically fusing UAV-derived hyperspectral imaging (HSI) and LiDAR data for CNC and AGNA monitoring. Results showed that the response of nitrogen status indicators to fertilization was phenology-specific: CNC showed no significant difference (p > 0.05) among treatments during the vigorous vegetative growth stage (VGS) but differed significantly (p < 0.05) during the fruit expansion stage (FES); AGNA differed significantly among treatments at VGS and FES (p < 0.05). The two-step screening yielded NDSI (732, 879) and NDSI (560, 690) as the optimal CNC indicators at VGS and FES, respectively (r = 0.83 and 0.93), whereas the NDSI (711, 986) and NDSI (515, 736) were identified as the optimal AGNA indicators at VGS and FES, respectively (r = 0.91 and 0.71). Across all phenological stages, Random Forest Regression consistently delivered the highest accuracy for CNC (R2 = 0.93-0.98, RMSE = 0.87-1.02 g kg-1) and AGNA (R2 = 0.95-0.97, RMSE = 1.92-2.55 g plant-1), outperforming MLR, PLSR, and SVR. This synergistic framework provides a high-precision, non-destructive methodology for the precision N monitoring of woody crops.

Brown marmorated stink bug (BMSB), Halyomorpha halys (Stål) (Hemiptera: Pentatomidae), severely impacts global hazelnut production, especially in Türkiye, the top producer, and Oregon, USA. This study analyzed seasonal BMSB population dynamics and damage types on hazelnut fruiting bodies across phenological stages. Field monitoring in Oregon's Willamette Valley (2014-2016) and Türkiye's Eastern Black Sea region (2019-2021) showed distinct seasonal activity patterns. Hazelnut phenology in Türkiye advances 6 weeks earlier than in Oregon with higher heat accumulation sustaining BMSB activity post-harvest. Semi-field cage experiments conducted in 2022 in Türkiye quantified insect-induced damage in relation to nut development. Five distinct damage types were identified: shell malformation (4.7%) in May-June, blank black shell (2.2%) and empty kernel (6.5%) in June, shriveled kernel (8.4%) in late June-mid-July, and corked kernel (10.5%) in July-August. A single adult was capable of damaging up to 537 nuts per season, with losses reaching 85% during the kernel expansion stage. Damage increased progressively through the season, with total damage 1.6-fold higher during kernel expansion compared to early development. Corked kernel damage was uniquely associated with BMSB feeding, confirming its diagnostic value. Findings demonstrate that BMSB injury is strongly shaped by the timing of insect activity relative to hazelnut phenology, with peak mid- to late-season activity driving greater losses, particularly in late-maturing cultivars. By linking damage types with per-capita impact, this study defines critical intervention windows for integrated pest management and highlights the need for adaptive forecasting tools that integrate pest biology, climate, and crop phenology.

• The angular sensitivity of SIF and VIs was quantified across winter wheat phenology. • Stronger angular variability of SIF than VIs was identified (CV up to 75.3%). • Angular effects on yield estimation were assessed using a multi-head attention LSTM. • The combined VIs + SIF achieved the highest accuracy and angular robustness. Accurate crop yield estimation is crucial for ensuring global food security. The integration of solar-induced chlorophyll fluorescence (SIF) with traditional vegetation indices (VIs) has shown great potential in yield prediction, yet how data-layer uncertainties propagate and impact model performance remains unclear. Using winter wheat as the target crop, we first quantified the angular sensitivity of SIF and several key VIs within the two-dimensional solar zenith angle (SZA)-viewing zenith angle (VZA) domain and examined its evolution across phenological stages. Subsequently, three models (VIs_Only, SIF_Only, and VIs + SIF) were developed for the Guanzhong Plain using a multi-head self-attention Long Short-Term Memory (LSTM) framework, and their performance dependency on observation geometry was systematically evaluated. The results show that: (1) SIF exhibited markedly stronger angular sensitivity than the VIs (CV up to 75.3%), with the highest instability under dual-oblique geometries (high SZA and VZA) and increasing with canopy development; (2) this angular variability propagated into the models, causing a significant accuracy decline for the SIF_Only model under dual-oblique conditions; (3) SIF provided key phenological complementarity: when VIs saturated (mid-to-late stage), SIF inclusion substantially increased model R 2 ; and (4) the VIs + SIF fusion was the optimal strategy for accuracy and robustness (R 2 = 0.40, RMSE = 568.35 kg/ha). The combined model achieved the highest precision and used VIs as a stabilizer to compensate for SIF ’ s angular uncertainty, maintaining robustness across all geometries. This study quantitatively demonstrates the impact of angular variability on yield estimation and highlights that synergizing SIF and VIs can substantially enhance accuracy and robustness, providing important guidance for future satellite strategies, sensor design, and agricultural applications.