Temperature dependence of pollen germination and tube growth in conifers relates to their distribution along an elevational gradient in Washington State, USA.

BACKGROUND AND AIMS: Pollen germination and tube growth are essential processes for successful fertilization. They are among the most temperature-vulnerable stages and subsequently affect seed production and determine population persistence and species distribution under climate change. Our study aims to investigate intra- and inter-specific variations in the temperature dependence of pollen germination and tube length growth and to explore how these variations differ for pollen from elevational gradients. METHODS: We focused on three conifer species, Pinus contorta, Picea engelmannii, and Pinus ponderosa, with pollen collected from 350 to 2200m elevation in Washington State, USA. We conducted pollen viability tests at temperatures from 5 to 40°C in 5°C intervals. After testing for four days, we took images of these samples under a microscope to monitor pollen germination percentage (GP) and tube length (TL). We applied the Gamma function to describe the temperature dependence of GP and TL and estimated key parameters, including the optimal temperature for GP (Topt_GP) and TL (Topt_TL). KEY RESULTS: Results showed that pollen from three species and different elevations within a species have different GP, TL, Topt_GP, and Topt_TL. The population with a higher Topt_GP would also have a higher Topt_TL, while Topt_TL was generally higher than Topt_GP, i.e., a positive but not one-to-one relationship. However, only Pinus contorta showed that populations from higher elevations have lower Topt_GP and Topt_TL and vice versa. The variability in GP increased at extreme temperatures, whereas the variability in TL was greatest near Topt_TL. CONCLUSIONS: Our study demonstrates the temperature dependences of three conifers across a wide range of temperatures. Pollen germination and tube growth are highly sensitive to temperature conditions and vary among species and elevations, affecting their reproduction success during warming. Our findings can provide valuable insights to advance our understanding of how conifer pollen responds to rising temperatures.

A comparison between centralized and asynchronous federated learning approaches for survival outcome prediction using clinical and PET data from non-small cell lung cancer patients.

BACKGROUND AND OBJECTIVE: Survival analysis plays an essential role in the medical field for optimal treatment decision-making. Recently, survival analysis based on the deep learning (DL) approach has been proposed and is demonstrating promising results. However, developing an ideal prediction model requires integrating large datasets across multiple institutions, which poses challenges concerning medical data privacy. METHODS: In this paper, we propose FedSurv, an asynchronous federated learning (FL) framework designed to predict survival time using clinical information and positron emission tomography (PET)-based features. This study used two datasets: a public radiogenic dataset of non-small cell lung cancer (NSCLC) from the Cancer Imaging Archive (RNSCLC), and an in-house dataset from the Chonnam National University Hwasun Hospital (CNUHH) in South Korea, consisting of clinical risk factors and F-18 fluorodeoxyglucose (FDG) PET images in NSCLC patients. Initially, each dataset was divided into multiple clients according to histological attributes, and each client was trained using the proposed DL model to predict individual survival time. The FL framework collected weights and parameters from the clients, which were then incorporated into the global model. Finally, the global model aggregated all weights and parameters and redistributed the updated model weights to each client. We evaluated different frameworks including single-client-based approach, centralized learning and FL. RESULTS: We evaluated our method on two independent datasets. First, on the RNSCLC dataset, the mean absolute error (MAE) was 490.80±22.95 d and the C-Index was 0.69±0.01. Second, on the CNUHH dataset, the MAE was 494.25±40.16 d and the C-Index was 0.71±0.01. The FL approach achieved centralized method performance in PET-based survival time prediction and outperformed single-client-based approaches. CONCLUSIONS: Our results demonstrated the feasibility and effectiveness of employing FL for individual survival prediction in NSCLC patients, using clinical information and PET-based features.

Surgical outcomes and survival of patients over 80 years old who underwent curative resection for gastric cancer.

Purpose: Among patients with gastric cancer who underwent radical gastrectomy, the proportion of patients aged ≥80 years has increased. This study aimed to evaluate surgical outcomes and survival of patients aged ≥80 years who underwent curative resection for gastric cancer and identify independent factors that affect postoperative survival. Methods: This retrospective study enrolled 1,066 patients aged ≥65 years with gastric cancer who underwent curative resection between January 2014 and December 2018 at a single institution. They were divided into those aged ≥80 years (old-elderly group) and 65-79 years (young-elderly group). Their clinicopathological characteristics and surgical outcomes were compared. Results: Of the 1,066 patients, 136 (12.8%) were 80 years or older. Higher American Society of Anesthesiologists (ASA) physical status classification and more advanced cancers were observed in the old-elderly group than in the young-elderly group. No significant difference in postoperative complications was found between the groups. At a median follow-up of 49.1 months, the 5-year overall survival rate after surgery for the old-elderly group was lower than that for the young-elderly group (75.6% vs. 87.0%, P < 0.001). However, the 5-year disease-specific survival rate was comparable between the groups (90.1% vs. 92.2%, P = 0.324). ASA physical status classification, pathologic stage, and surgical approach were independent predictors of overall survival. Conclusion: Old-elderly patients aged ≥80 years had comparable postoperative outcomes and disease-specific survival to the young-elderly group, suggesting that curative gastrectomy can be considered a viable option for octogenarian patients with gastric cancer.

Bridging Time-series Image Phenotyping and Functional-Structural Plant Modeling to Predict Adventitious Root System Architecture.

Root system architecture (RSA) is an important measure of how plants navigate and interact with the soil environment. However, current methods in studying RSA must make tradeoffs between precision of data and proximity to natural conditions, with root growth in germination papers providing accessibility and high data resolution. Functional-structural plant models (FSPMs) can overcome this tradeoff, though parameterization and evaluation of FSPMs are traditionally based in manual measurements and visual comparison. Here, we applied a germination paper system to study the adventitious RSA and root phenology of Populus trichocarpa stem cuttings using time-series image-based phenotyping augmented by FSPM. We found a significant correlation between timing of root initiation and thermal time at cutting collection (P value = 0.0061, R2 = 0.875), but little correlation with RSA. We also present a use of RhizoVision [1] for automatically extracting FSPM parameters from time series images and evaluating FSPM simulations. A high accuracy of the parameterization was achieved in predicting 2D growth with a sensitivity rate of 83.5%. This accuracy was lost when predicting 3D growth with sensitivity rates of 38.5% to 48.7%, while overall accuracy varied with phenotyping methods. Despite this loss in accuracy, the new method is amenable to high throughput FSPM parameterization and bridges the gap between advances in time-series phenotyping and FSPMs.

Robust Human Face Emotion Classification Using Triplet-Loss-Based Deep CNN Features and SVM.

Human facial emotion detection is one of the challenging tasks in computer vision. Owing to high inter-class variance, it is hard for machine learning models to predict facial emotions accurately. Moreover, a person with several facial emotions increases the diversity and complexity of classification problems. In this paper, we have proposed a novel and intelligent approach for the classification of human facial emotions. The proposed approach comprises customized ResNet18 by employing transfer learning with the integration of triplet loss function (TLF), followed by SVM classification model. Using deep features from a customized ResNet18 trained with triplet loss, the proposed pipeline consists of a face detector used to locate and refine the face bounding box and a classifier to identify the facial expression class of discovered faces. RetinaFace is used to extract the identified face areas from the source image, and a ResNet18 model is trained on cropped face images with triplet loss to retrieve those features. An SVM classifier is used to categorize the facial expression based on the acquired deep characteristics. In this paper, we have proposed a method that can achieve better performance than state-of-the-art (SoTA) methods on JAFFE and MMI datasets. The technique is based on the triplet loss function to generate deep input image features. The proposed method performed well on the JAFFE and MMI datasets with an accuracy of 98.44% and 99.02%, respectively, on seven emotions; meanwhile, the performance of the method needs to be fine-tuned for the FER2013 and AFFECTNET datasets.

Perennial grass root system specializes for multiple resource acquisitions with differential elongation and branching patterns.

Roots optimize the acquisition of limited soil resources, but relationships between root forms and functions have often been assumed rather than demonstrated. Furthermore, how root systems co-specialize for multiple resource acquisitions is unclear. Theory suggests that trade-offs exist for the acquisition of different resource types, such as water and certain nutrients. Measurements used to describe the acquisition of different resources should then account for differential root responses within a single system. To demonstrate this, we grew Panicum virgatum in split-root systems that vertically partitioned high water availability from nutrient availability so that root systems must absorb the resources separately to fully meet plant demands. We evaluated root elongation, surface area, and branching, and we characterized traits using an order-based classification scheme. Plants allocated approximately 3/4th of primary root length towards water acquisition, whereas lateral branches were progressively allocated towards nutrients. However, root elongation rates, specific root length, and mass fraction were similar. Our results support the existence of differential root functioning within perennial grasses. Similar responses have been recorded in many plant functional types suggesting a fundamental relationship. Root responses to resource availability can be incorporated into root growth models via maximum root length and branching interval parameters.

A Review of Machine Learning and Deep Learning Approaches on Mental Health Diagnosis.

Combating mental illnesses such as depression and anxiety has become a global concern. As a result of the necessity for finding effective ways to battle these problems, machine learning approaches have been included in healthcare systems for the diagnosis and probable prediction of the treatment outcomes of mental health conditions. With the growing interest in machine and deep learning methods, analysis of existing work to guide future research directions is necessary. In this study, 33 articles on the diagnosis of schizophrenia, depression, anxiety, bipolar disorder, post-traumatic stress disorder (PTSD), anorexia nervosa, and attention deficit hyperactivity disorder (ADHD) were retrieved from various search databases using the preferred reporting items for systematic reviews and meta-analysis (PRISMA) review methodology. These publications were chosen based on their use of machine learning and deep learning technologies, individually assessed, and their recommended methodologies were then classified into the various disorders included in this study. In addition, the difficulties encountered by the researchers are discussed, and a list of some public datasets is provided.

An Integrative Process-Based Model for Biomass and Yield Estimation of Hardneck Garlic (Allium sativum).

We introduce an integrative process-based crop model for garlic (Allium sativum). Building on our previous model that simulated key phenological, morphological, and physiological features of a garlic plant, the new garlic model provides comprehensive and integrative estimations of biomass accumulation and yield formation under diverse environmental conditions. This model also showcases an application of Cropbox to develop a comprehensive crop model. Cropbox is a crop modeling framework featuring declarative modeling language and a unified simulation interface for building and improving crop models. Using Cropbox, we first evaluated the model performance against three datasets with an emphasis on biomass and yield measured under different environmental conditions and growing seasons. We then applied the model to simulate optimal planting dates under future climate conditions for assessing climate adaptation strategies between two contrasting locations in South Korea: the current growing region (Gosan, Jeju) and an unfavorable cold winter region (Chuncheon, Gangwon). The model simulated the growth and development of a southern-type cultivar (Namdo, ND) reasonably well. Under Representative Concentration Pathway (RCP) scenarios, an overall delay in optimal planting date from a week to a month, and a slight increase in potential yield were expected in Gosan. Expansion of growing region to northern area including Chuncheon was expected due to mild winter temperatures in the future and may allow ND cultivar production in more regions. The predicted optimal planting date in the new region was similar to the current growing region that favors early fall planting. Our new integrative garlic model provides mechanistic, process-based crop responses to environmental cues and can be useful for assessing climate impacts and identifying crop specific climate adaptation strategies for the future.

Self-Relation Attention and Temporal Awareness for Emotion Recognition via Vocal Burst.

Speech emotion recognition (SER) is one of the most exciting topics many researchers have recently been involved in. Although much research has been conducted recently on this topic, emotion recognition via non-verbal speech (known as the vocal burst) is still sparse. The vocal burst is concise and has meaningless content, which is harder to deal with than verbal speech. Therefore, in this paper, we proposed a self-relation attention and temporal awareness (SRA-TA) module to tackle this problem with vocal bursts, which could capture the dependency in a long-term period and focus on the salient parts of the audio signal as well. Our proposed method contains three main stages. Firstly, the latent features are extracted using a self-supervised learning model from the raw audio signal and its Mel-spectrogram. After the SRA-TA module is utilized to capture the valuable information from latent features, all features are concatenated and fed into ten individual fully-connected layers to predict the scores of 10 emotions. Our proposed method achieves a mean concordance correlation coefficient (CCC) of 0.7295 on the test set, which achieves the first ranking of the high-dimensional emotion task in the 2022 ACII Affective Vocal Burst Workshop & Challenge.

Effects of Multiple Filters on Liver Tumor Segmentation From CT Images.

Segmentation of liver tumors from Computerized Tomography (CT) images remains a challenge due to the natural variation in tumor shape and structure as well as the noise in CT images. A key assumption is that the performance of liver tumor segmentation depends on the characteristics of multiple features extracted from multiple filters. In this paper, we design an enhanced approach based on a two-class (liver, tumor) convolutional neural network that discriminates tumor as well as liver from CT images. First, the contrast and intensity values in CT images are adjusted and high frequencies are removed using Hounsfield units (HU) filtering and standardization. Then, the liver tumor is segmented from entire images with multiple filter U-net (MFU-net). Finally, a quantitative analysis is carried out to evaluate the segmentation results using three different methods: boundary-distance-based metrics, size-based metrics, and overlap-based metrics. The proposed method is validated on CT images from the 3Dircadb and LiTS dataset. The results demonstrate that the multiple filters are useful for extracting local and global feature simultaneously, minimizing the boundary distance errors, and our approach demonstrates better performance in heterogeneous tumor regions of CT images.

EEG-Based Emotion Recognition by Convolutional Neural Network with Multi-Scale Kernels.

Besides facial or gesture-based emotion recognition, Electroencephalogram (EEG) data have been drawing attention thanks to their capability in countering the effect of deceptive external expressions of humans, like faces or speeches. Emotion recognition based on EEG signals heavily relies on the features and their delineation, which requires the selection of feature categories converted from the raw signals and types of expressions that could display the intrinsic properties of an individual signal or a group of them. Moreover, the correlation or interaction among channels and frequency bands also contain crucial information for emotional state prediction, and it is commonly disregarded in conventional approaches. Therefore, in our method, the correlation between 32 channels and frequency bands were put into use to enhance the emotion prediction performance. The extracted features chosen from the time domain were arranged into feature-homogeneous matrices, with their positions following the corresponding electrodes placed on the scalp. Based on this 3D representation of EEG signals, the model must have the ability to learn the local and global patterns that describe the short and long-range relations of EEG channels, along with the embedded features. To deal with this problem, we proposed the 2D CNN with different kernel-size of convolutional layers assembled into a convolution block, combining features that were distributed in small and large regions. Ten-fold cross validation was conducted on the DEAP dataset to prove the effectiveness of our approach. We achieved the average accuracies of 98.27% and 98.36% for arousal and valence binary classification, respectively.

Esophagus Segmentation in CT Images via Spatial Attention Network and STAPLE Algorithm.

One essential step in radiotherapy treatment planning is the organ at risk of segmentation in Computed Tomography (CT). Many recent studies have focused on several organs such as the lung, heart, esophagus, trachea, liver, aorta, kidney, and prostate. However, among the above organs, the esophagus is one of the most difficult organs to segment because of its small size, ambiguous boundary, and very low contrast in CT images. To address these challenges, we propose a fully automated framework for the esophagus segmentation from CT images. The proposed method is based on the processing of slice images from the original three-dimensional (3D) image so that our method does not require large computational resources. We employ the spatial attention mechanism with the atrous spatial pyramid pooling module to locate the esophagus effectively, which enhances the segmentation performance. To optimize our model, we use group normalization because the computation is independent of batch sizes, and its performance is stable. We also used the simultaneous truth and performance level estimation (STAPLE) algorithm to reach robust results for segmentation. Firstly, our model was trained by k-fold cross-validation. And then, the candidate labels generated by each fold were combined by using the STAPLE algorithm. And as a result, Dice and Hausdorff Distance scores have an improvement when applying this algorithm to our segmentation results. Our method was evaluated on SegTHOR and StructSeg 2019 datasets, and the experiment shows that our method outperforms the state-of-the-art methods in esophagus segmentation. Our approach shows a promising result in esophagus segmentation, which is still challenging in medical analyses.

Age estimation based on 3D post-mortem computed tomography images of mandible and femur using convolutional neural networks.

Age assessment has attracted increasing attention in the field of forensics. However, most existing works are laborious and requires domain-specific knowledge. Modern computing power makes it is possible to leverage massive amounts of data to produce more reliable results. Therefore, it is logical to use automated age estimation approaches to handle large datasets. In this study, a fully automated age prediction approach was proposed by assessing 3D mandible and femur scans using deep learning. A total of 814 post-mortem computed tomography scans from 619 men and 195 women, within the age range of 20-70, were collected from the National Forensic Service in South Korea. Multiple preprocessing steps were applied for each scan to normalize the image and perform intensity correction to create 3D voxels that represent these parts accurately. The accuracy of the proposed method was evaluated by 10-fold cross-validation. The initial cross-validation results illustrated the potential of the proposed method as it achieved a mean absolute error of 5.15 years with a concordance correlation coefficient of 0.80. The proposed approach is likely to be faster and potentially more reliable, which could be used for age assessment in the future.

Multi-Level Seg-Unet Model with Global and Patch-Based X-ray Images for Knee Bone Tumor Detection.

Tumor classification and segmentation problems have attracted interest in recent years. In contrast to the abundance of studies examining brain, lung, and liver cancers, there has been a lack of studies using deep learning to classify and segment knee bone tumors. In this study, our objective is to assist physicians in radiographic interpretation to detect and classify knee bone regions in terms of whether they are normal, begin-tumor, or malignant-tumor regions. We proposed the Seg-Unet model with global and patched-based approaches to deal with challenges involving the small size, appearance variety, and uncommon nature of bone lesions. Our model contains classification, tumor segmentation, and high-risk region segmentation branches to learn mutual benefits among the global context on the whole image and the local texture at every pixel. The patch-based model improves our performance in malignant-tumor detection. We built the knee bone tumor dataset supported by the physicians of Chonnam National University Hospital (CNUH). Experiments on the dataset demonstrate that our method achieves better performance than other methods with an accuracy of 99.05% for the classification and an average Mean IoU of 84.84% for segmentation. Our results showed a significant contribution to help the physicians in knee bone tumor detection.

Context-Aware Emotion Recognition in the Wild Using Spatio-Temporal and Temporal-Pyramid Models.

Emotion recognition plays an important role in human-computer interactions. Recent studies have focused on video emotion recognition in the wild and have run into difficulties related to occlusion, illumination, complex behavior over time, and auditory cues. State-of-the-art methods use multiple modalities, such as frame-level, spatiotemporal, and audio approaches. However, such methods have difficulties in exploiting long-term dependencies in temporal information, capturing contextual information, and integrating multi-modal information. In this paper, we introduce a multi-modal flexible system for video-based emotion recognition in the wild. Our system tracks and votes on significant faces corresponding to persons of interest in a video to classify seven basic emotions. The key contribution of this study is that it proposes the use of face feature extraction with context-aware and statistical information for emotion recognition. We also build two model architectures to effectively exploit long-term dependencies in temporal information with a temporal-pyramid model and a spatiotemporal model with "Conv2D+LSTM+3DCNN+Classify" architecture. Finally, we propose the best selection ensemble to improve the accuracy of multi-modal fusion. The best selection ensemble selects the best combination from spatiotemporal and temporal-pyramid models to achieve the best accuracy for classifying the seven basic emotions. In our experiment, we take benchmark measurement on the AFEW dataset with high accuracy.

Making Waxy Salts in Water: Synthetic Control of Hydrophobicity for Anion-Induced and Aggregation-Enhanced Light Emission.

We show that multipodal polycationic receptors function as anion-responsive light-emitters in water. Prevailing paradigms utilize rigid holes and cavities for ion recognition. We instead built open amphiphilic scaffolds that trigger polar-to-nonpolar environment transitions around cationic fluorophores upon anion complexation. This ion-pairing and aggregation event produces a dramatic enhancement in the emission intensity, as demonstrated by perchlorate as a non-spherical hydrophobic anion model. A synergetic interplay of C-H⋅⋅⋅anion hydrogen bonding and tight anion-π+ contacts underpins this supramolecular phenomenon. By changing the aliphatic chain length, we demonstrate that the response profile and threshold of this signaling event can be controlled at the molecular level. With appropriate molecular design, inherently weak, ill-defined, and non-directional van der Waals interaction enables selective, sensitive, and tunable recognition in water.

Proton Switch in the Secondary Coordination Sphere to Control Catalytic Events at the Metal Center: Biomimetic Oxo Transfer Chemistry of Nickel Amidate Complex.

High-valent metal-oxo species are key intermediates for the oxygen atom transfer step in the catalytic cycles of many metalloenzymes. While the redox-active metal centers of such enzymes are typically supported by anionic amino acid side chains or porphyrin rings, peptide backbones might function as strong electron-donating ligands to stabilize high oxidation states. To test the feasibility of this idea in synthetic settings, we have prepared a nickel(II) complex of new amido multidentate ligand. The mononuclear nickel complex of this N5 ligand catalyzes epoxidation reactions of a wide range of olefins by using mCPBA as a terminal oxidant. Notably, a remarkably high catalytic efficiency and selectivity were observed for terminal olefin substrates. We found that protonation of the secondary coordination sphere serves as the entry point to the catalytic cycle, in which high-valent nickel species is subsequently formed to carry out oxo-transfer reactions. A conceptually parallel process might allow metalloenzymes to control the catalytic cycle in the primary coordination sphere by using proton switch in the secondary coordination sphere.

Altered arsenic availability, uptake, and allocation in rice under elevated temperature.

Climate change is expected to increase growing temperatures in rice cultivating regions worldwide. Recent research demonstrates that elevated temperature can increase arsenic concentrations in rice tissue, exacerbating an existing threat to rice quality and human health. However, the specific temperature-induced changes in the plant-soil system responsible for increased arsenic concentrations remain unclear and such knowledge is necessary to manage human dietary arsenic exposure in a warmer future. To elucidate these changes, we established four temperature treatments in climate-controlled growth chambers and grew rice plants (Oryza sativa cv. M206) in pots filled with Californian paddy soil with arsenic concentrations of 7.7 mg kg-1. The four chosen temperatures mimicked IPCC forecasting for Northern California, with a roughly 2.5 °C increase between treatments (nighttime temperatures ~2 °C cooler). We observed that arsenic concentrations in porewater, root iron plaque, and plant tissue increased in response to elevated temperature. There was a positive linear relationship between temperature and rice grain arsenic, almost all of which was present as inorganic As (III). Above-ground allocation patterns were consistent across treatments. We found no upregulation in the gene encoding the OsABCC1 transporter, believed to be important for arsenic sequestration in vacuoles and thereby preventing arsenic transfer to grain. Rice plants grown at higher temperatures had more adsorbed arsenic per unit of iron plaque (measured as [As]/[Fe]), indicating temperature may impact arsenic sorption to root plaque. We present evidence that increased soil mobilization of arsenic was the driving factor responsible for increased arsenic uptake into rice grain. Transpiration, which can increase arsenic transport to roots, was also heightened with elevated temperature but appeared to play a secondary role. Our system had low soil arsenic concentrations typical for California. Our findings highlight that elevated growing temperatures may increase the risk of dietary arsenic exposure in rice systems that were previously considered low risk.

Coupled Gas-Exchange Model for C4 Leaves Comparing Stomatal Conductance Models.

Plant simulation models are abstractions of plant physiological processes that are useful for investigating the responses of plants to changes in the environment. Because photosynthesis and transpiration are fundamental processes that drive plant growth and water relations, a leaf gas-exchange model that couples their interdependent relationship through stomatal control is a prerequisite for explanatory plant simulation models. Here, we present a coupled gas-exchange model for C4 leaves incorporating two widely used stomatal conductance submodels: Ball-Berry and Medlyn models. The output variables of the model includes steady-state values of CO2 assimilation rate, transpiration rate, stomatal conductance, leaf temperature, internal CO2 concentrations, and other leaf gas-exchange attributes in response to light, temperature, CO2, humidity, leaf nitrogen, and leaf water status. We test the model behavior and sensitivity, and discuss its applications and limitations. The model was implemented in Julia programming language using a novel modeling framework. Our testing and analyses indicate that the model behavior is reasonably sensitive and reliable in a wide range of environmental conditions. The behavior of the two model variants differing in stomatal conductance submodels deviated substantially from each other in low humidity conditions. The model was capable of replicating the behavior of transgenic C4 leaves under moderate temperatures as found in the literature. The coupled model, however, underestimated stomatal conductance in very high temperatures. This is likely an inherent limitation of the coupling approaches using Ball-Berry type models in which photosynthesis and stomatal conductance are recursively linked as an input of the other.

Modelling climate change impacts on maize yields under low nitrogen input conditions in sub-Saharan Africa.

Smallholder farmers in sub-Saharan Africa (SSA) currently grow rainfed maize with limited inputs including fertilizer. Climate change may exacerbate current production constraints. Crop models can help quantify the potential impact of climate change on maize yields, but a comprehensive multimodel assessment of simulation accuracy and uncertainty in these low-input systems is currently lacking. We evaluated the impact of varying [CO2 ], temperature and rainfall conditions on maize yield, for different nitrogen (N) inputs (0, 80, 160 kg N/ha) for five environments in SSA, including cool subhumid Ethiopia, cool semi-arid Rwanda, hot subhumid Ghana and hot semi-arid Mali and Benin using an ensemble of 25 maize models. Models were calibrated with measured grain yield, plant biomass, plant N, leaf area index, harvest index and in-season soil water content from 2-year experiments in each country to assess their ability to simulate observed yield. Simulated responses to climate change factors were explored and compared between models. Calibrated models reproduced measured grain yield variations well with average relative root mean square error of 26%, although uncertainty in model prediction was substantial (CV = 28%). Model ensembles gave greater accuracy than any model taken at random. Nitrogen fertilization controlled the response to variations in [CO2 ], temperature and rainfall. Without N fertilizer input, maize (a) benefited less from an increase in atmospheric [CO2 ]; (b) was less affected by higher temperature or decreasing rainfall; and (c) was more affected by increased rainfall because N leaching was more critical. The model intercomparison revealed that simulation of daily soil N supply and N leaching plays a crucial role in simulating climate change impacts for low-input systems. Climate change and N input interactions have strong implications for the design of robust adaptation approaches across SSA, because the impact of climate change in low input systems will be modified if farmers intensify maize production with balanced nutrient management.