Using artificial neural networks to predict future dryland responses to human and climate disturbances

Profiling of Tumor-Infiltrating Immune Cells and Their Impact on Survival in Glioblastoma Patients Undergoing Immunotherapy with Dendritic Cells

Glioblastomas (GBM) are the most common primary malignant brain tumors, comprising 2% of all cancers in adults. Their location and cellular and molecular heterogeneity, along with their highly infiltrative nature, make their treatment challenging. Recently, our research group reported promising results from a prospective phase II clinical trial involving allogeneic vaccination with dendritic cells (DCs). To date, six out of the thirty-seven reported cases remain alive without tumor recurrence. In this study, we focused on the characterization of infiltrating immune cells observed at the time of surgical resection. An analytical model employing a neural network-based predictive algorithm was used to ascertain the potential prognostic implications of immunological variables on patients' overall survival. Counterintuitively, immune phenotyping of tumor-associated macrophages (TAMs) has revealed the extracellular marker PD-L1 to be a positive predictor of overall survival. In contrast, the elevated expression of CD86 within this cellular subset emerged as a negative prognostic indicator. Fundamentally, the neural network algorithm outlined here allows a prediction of the responsiveness of patients undergoing dendritic cell vaccination in terms of overall survival based on clinical parameters and the profile of infiltrated TAMs observed at the time of tumor excision.

Prediction and monitoring of LULC shift using cellular automata-artificial neural network in Jumar watershed of Ranchi District, Jharkhand

Jumar watershed of Ranchi district is agrarian in nature. The unplanned and exponentially growing urban sprawl has become one of the probable threats in achieving sustainable development goals (SDG-15). The purpose of this research study is to monitor the urban sprawl in Jumar watershed within three decades i.e. from the year 1990 to 2021. Land use land cover (LULC) change has been monitored using satellite data from LANDSAT (4, 5 and 8). Various indices are calculated like normalised difference vegetation index (NDVI), normalised difference built-up index (NDBI), normalised difference water index (NDWI) and built-up index (BUI) to monitor LULC change in the area. For prediction of urban sprawl, cellular automata and artificial neural network (CA-ANN) with GIS application technique is used. The model is validated by using Kappa coefficient. The prediction results showed increase in built-up area by 8.23 sq. km in the next decade. The built-up and barren land together increase up to 42.85 sq. km by 2030 and 34.61 sq. km in 2021. The NDVI for 3-decade period showed significant decrease in the healthy vegetation and increase in sparse vegetation. The NDBI showed a slight increase in urban area but massive increase in uncultivated and barren land. NDWI showed a decrease in area of the surface water. The LULC studies showed a major shift from healthy vegetation to agriculture and then to barren land. To assess the impact of urbanisation on water quality, water samples are taken seasonally from J1to J11 sampling locations and are analysed as per APHA procedure. The sites are classified as urban, semi urban and rural area as per their location. The water quality index (WQI) varied between 42.14 to 61.42 during pre-monsoon, 62.20 to 68.7995 during monsoon and 43.48 to 60.12 during post-monsoon. The quality of water is found poor in all seasons at all sampling sites. The water is found highly turbid and alkaline throughout the year. Overall, it can be concluded that the water needs to be pre-treated for drinking purposes throughout the year.

Clair SI, Bratsman S, Merritt M, Norris AJ, Carling GT, Hansen N, St. Clair SB, Abbott BW. Megafire affects stream sediment flux and dissolved organic matter reactivity, but land use dominates nutrient dynamics in semiarid watersheds

Climate change is causing larger wildfires and more extreme precipitation events in many regions. As these ecological disturbances increasingly coincide, they alter lateral fluxes of sediment, organic matter, and nutrients. Here, we report the stream chemistry response of watersheds in a semiarid region of Utah (USA) that were affected by a megafire followed by an extreme precipitation event in October 2018. We analyzed daily to hourly water samples at 10 stream locations from before the storm event until three weeks after its conclusion for suspended sediment, solute and nutrient concentrations, water isotopes, and dissolved organic matter concentration, optical properties, and reactivity. The megafire caused a ~2,000-fold increase in sediment flux and a ~6,000-fold increase in particulate carbon and nitrogen flux over the course of the storm. Unexpectedly, dissolved organic carbon (DOC) concentration was 2.1-fold higher in burned watersheds, despite the decreased organic matter from the fire. DOC from burned watersheds was 1.3-fold more biodegradable and 2.0-fold more photodegradable than in unburned watersheds based on 28-day dark and light incubations. Regardless of burn status, nutrient concentrations were higher in watersheds with greater urban and agricultural land use. Likewise, human land use had a greater effect than megafire on apparent hydrological residence time, with rapid stormwater signals in urban and agricultural areas but a gradual stormwater pulse in areas without direct human influence. These findings highlight how megafires and intense rainfall increase short-term particulate flux and alter organic matter concentration and characteristics. However, in contrast with previous research, which has largely focused on burned-unburned comparisons in pristine watersheds, we found that direct human influence exerted a primary control on nutrient status. Reducing anthropogenic nutrient sources could therefore increase socioecological resilience of surface water networks to changing wildfire regimes.

Multi-Year NDVI Values as Indicator of the Relationship between Spatiotemporal Vegetation Dynamics and Environmental Factors in the Qaidam Basin, China

The Qaidam Basin is a unique and complex ecosystem, wherein elevation gradients lead to high spatial heterogeneity in vegetation dynamics and responses to environmental factors. Based on the remote sensing data of Moderate Resolution Imaging Spectroradiometer (MODIS), Tropical Rainfall Measuring Mission (TRMM) and Global Land Data Assimilation System (GLDAS), we analyzed the spatiotemporal variations of vegetation dynamics and responses to precipitation, accumulative temperature (AT) and soil moisture (SM) in the Qaidam Basin from 2001 to 2016. Moreover, the contribution of those factors to vegetation dynamics at different altitudes was analyzed via an artificial neural network (ANN) model. The results indicated that the Normalized Difference Vegetation Index (NDVI) values in the growing season showed an overall upward trend, with an increased rate of 0.001/year. The values of NDVI in low-altitude areas were higher than that in high-altitude areas, and the peak values of NDVI appeared along the elevation gradient at 4400–4600 m. Thanks to the use of ANN, we were able to detect the relative contribution of various environmental factors; the relative contribution rate of AT to the NDVI dynamic was the most significant (35.17%) in the low-elevation region (<2900 m). In the mid-elevation area (2900–3900 m), precipitation contributed 44.76% of the NDVI dynamics. When the altitude was higher than 3900 m, the relative contribution rates of AT (39.50%) and SM (38.53%) had no significant difference but were significantly higher than that of precipitation (21.97%). The results highlight that the different environmental factors have various contributions to vegetation dynamics at different altitudes, which has important theoretical and practical significance for regulating ecological processes.

Historic and Simulated Desert-Oasis Ecotone Changes in the Arid Tarim River Basin, China

The desert-oasis ecotone, as a crucial natural barrier, maintains the stability of oasis agricultural production and protects oasis habitat security. This paper investigates the dynamic evolution of the desert-oasis ecotone in the Tarim River Basin and predicts the near-future land-use change in the desert-oasis ecotone using the cellular automata–Markov (CA-Markov) model. Results indicate that the overall area of the desert-oasis ecotone shows a shrinking trend (from 67,642 km2 in 1990 to 46,613 km2 in 2015) and the land-use change within the desert-oasis ecotone is mainly manifested by the conversion of a large amount of forest and grass area into arable land. The increasing demand for arable land for groundwater has led to a decline in the groundwater level, which is an important reason for the habitat deterioration in the desert-oasis ecotone. The rising temperature and drought have further exacerbated this trend. Assuming the current trend in development without intervention, the CA-Markov model predicts that by 2030, there will be an additional 1566 km2 of arable land and a reduction of 1151 km2 in forested area and grassland within the desert-oasis ecotone, which will inevitably further weaken the ecological barrier role of the desert-oasis ecotone and trigger a growing ecological crisis.

Accuracy, uncertainty, and interpretability assessments of ANFIS models to predict dust concentration in semi-arid regions

Accurate prediction of the dust concentration (DC) is necessary to reduce its undesirable environmental effects in different geographical areas. Although the adaptive neuro-fuzzy inference system (ANFIS) is a powerful model for predicting dust events, no attempt has been made to investigate its uncertainty and interpretability. In this study, therefore, the uncertainty of the ANFIS model was quantified using uncertainty estimation based on local errors and clustering methods. Furthermore, we used a model-agnostic interpretation to make the ANFIS model interpretable. In addition, we used the bat optimization algorithm (BAT) to increase the prediction accuracy of the ANFIS model. Seven explanatory variables were chosen for predicting DC in the cold and warm months across semi-arid regions of Iran. The results showed that the ANFIS+BAT model increased the correlation coefficient by 10% and 16% for predicting DC in the cold and warm months, respectively, compared with the ANFIS model. Furthermore, the uncertainty analysis indicated a lower prediction interval (i.e., lower uncertainty) for the ANFIS+BAT model compared with the ANFIS model for predicting DC in the cold and warm months. In addition, the model-agnostic interpretation tool findings indicated the highest contributions of air temperature and maximum wind speed for predicting DC in the cold and warm months, respectively. Prediction of DC using the proposed model will allow decision-makers to better plan for measures to mitigate the risks of wind erosion and air pollution.

Modeling the effects of precipitation and temperature patterns on agricultural drought in China from 1949 to 2015

Agricultural drought is one of the most frequent and widespread natural disasters occurring in China. Drought is associated with hydrological and meteorological conditions that lead to water-deficient vegetation, which has a negative effect on agricultural activities. The monitoring of droughts, as well as early-warning and timely information, is significant for crop production and food security. However, the spatial and temporal patterns of precipitation and temperature have rarely been reported when monitoring the agricultural drought loss rate on a national scale. In this study, we analyzed the spatial and temporal patterns of drought based on model simulation. An artificial neural network (ANN) model for drought warning was developed using monthly temperature and precipitation data from 1949 to 2015. Our results demonstrated that the agricultural drought loss rate can be simulated in most agricultural areas of China. Our ANN model simulation revealed that the areal percentages of precipitation and temperature are strongly correlated with agricultural drought, with the agricultural drought loss rate exhibiting greater sensitivity to precipitation than temperature. We suggest that the spatial and temporal patterns of precipitation are useful for capturing drought warning signals. The precipitation thresholds play an important role in detecting agricultural drought in critical months or seasons of crop growth in different regions. This study presents a framework and reference for drought monitoring in the regions and countries facing frequent agricultural drought.

A Simplified Climate Change Model and Extreme Weather Model Based on a Machine Learning Method

The emergence of climate change (CC) is affecting and changing the development of the natural environment, biological species, and human society. In order to better understand the influence of climate change and provide convincing evidence, the need to quantify the impact of climate change is urgent. In this paper, a climate change model is constructed by using a radial basis function (RBF) neural network. To verify the relevance between climate change and extreme weather (EW), the EW model was built using a support vector machine. In the case study of Canada, its level of climate change was calculated as being 0.2241 (“normal”), and it was found that the factors of CO2 emission, average temperature, and sea surface temperature are significant to Canada’s climate change. In 2025, the climate level of Canada will become “a little bad” based on the prediction results. Then, the Pearson correlation value is calculated as being 0.571, which confirmed the moderate positive correlation between climate change and extreme weather. This paper provides a strong reference for comprehensively understanding the influences brought about by climate change.

An Amazon stingless bee foraging activity predicted using recurrent artificial neural networks and attribute selection

Bees play a key role in pollination of crops and in diverse ecosystems. There have been multiple reports in recent years illustrating bee population declines worldwide. The search for more accurate forecast models can aid both in the understanding of the regular behavior and the adverse situations that may occur with the bees. It also may lead to better management and utilization of bees as pollinators. We address an investigation with Recurrent Neural Networks in the task of forecasting bees’ level of activity taking into account previous values of level of activity and environmental data such as temperature, solar irradiance and barometric pressure. We also show how different input time windows, algorithms of attribute selection and correlation analysis can help improve the accuracy of our model.