Latitude Longitude Research Articles

PEMBUATAN PETA DESA AIR MERAH KECAMATAN CURUP TENGAH KABUPATEN REJANG LEBONG BENGKULU

Maps are complex data sets containing information on the location and objects of an area. Maps can show the distribution of various things on Earth, such as settlement patterns, mountains and others. ArcGIS is software that can be used in making village maps. Air Merah village is a village in Curup Tengah sub-district, Bengkulu, which until now has not had complete mapping for the area. The purpose of this service is to help present village data that can be accessed as spatial data information in planning development progress in Air Merah Village. Community service is carried out in stages of visiting the village head's office for administrative processes, conducting discussions with the team, collecting data through field surveys and interviews, making maps, and discussing the results of thematic maps, as well as holding a presentation to discuss the results of the map and handing over map printouts to village officials. This service activity was attended by lecturers, partners and students who were involved in all series of services both in the field and discussions, so as to produce village information maps. Based on the results of field surveys and modeling, Air Merah Village has an area of ± 10.7789 km2 and is located at latitude longitude -3.4801, 102.556365. Map making has received a positive response from the surrounding community and is expected to be able to provide location information and improve the inventory of Air Merah Village.

Global Ionospheric Response During Extreme Geomagnetic Storm in May 2024

The main idea of the present study is to investigate in detail the time evolution of the spatial inhomogeneities connected with the ionospheric response to the geomagnetic storm registered in the period of 10–11 May 2024. The obtained ionospheric anomalies represented by the relative deviations of the global Total Electron Content (TEC) data have been utilized in the analysis. The used global TEC data have been converted to a coordinate system with a modip latitude and geographical longitude. In addition to the maps illustrating the global spatial distribution of the geomagnetically forced ionospheric anomalies, a presentation of the observed longitudinal structures by sinusoidal approximation has also been used. The resulting positive and negative responses have been studied depending on the magnetic latitude, local times and the behavior of the geomagnetic activity parameters during the considered event. The interpretation takes into account the known mechanisms for the effect of the geomagnetic storm on the electron density. A special attention is focused on the differences in the two hemispheres at high and mid latitudes, where a simultaneous direct impact of the particle precipitation and the change in the temperature regime of the neutral atmosphere has been assumed. The low-latitude response as a result of the Equatorial Ionization Anomaly (EIA) associated with Disturbed Dynamo Electric Fields (DDEFs) and its relationship with local time has also been considered.

Water ice particles detected by SELENE's Spectral Profiler at lunar shadowed regions in various local times and latitudes

Processes of water (OH and H2O) migration on the Moon remain unclear, prompting active research. Understanding lunar water migration requires investigation of the trapping and diffusion properties of water at various latitudes and local times. This study analyzed visible to near-infrared spectral data obtained by the Spectral Profiler (SP) onboard SELENE for shadowed regions at various local times and latitudes, not limited to the polar permanently shadowed regions. We assessed SP data for shadowed regions in 60 areas, each spanning a 10° × 10° latitude–longitude grid. Of the 1,061,907 analyzed shadowed-region data, 41,385 at various latitudes exhibited significant absorption in the 1.25 and 1.5 µm bands, indicating water ice particles. Data with the two absorption features suggest the presence of a water ice frost layer covering the lunar surface or suspended water ice particles above the lunar surface, at various latitude shadowed regions. Our spectral simulations have quantified the ice particles as being 0.1–1 µm in diameter, with a column density of 10–4–10–3 kg/m2. The spectral parameters for band absorption at the 1.5 µm band show symmetry between morning and evening sides, which is potentially attributed to the absence of variations in ice grain size and quantity. The 1.5 µm band absorption shows an increasing trend toward terminator regions, indicating variation in the water ice distribution and likely reflecting temperature conditions for water retention. The latitudinal trend of ice grain size and quantity remains uncertain because of the observed noise levels. Observations of water ice particles in shadowed regions at various latitudes and local times can provide new constraints on trapping and diffusion processes of lunar water migration.

GERB Obs4MIPs: a dataset for evaluating diurnal and monthly variations in top-of-atmosphere radiative fluxes in climate models

Abstract. A newly available radiative flux dataset specifically designed to enable the evaluation of the diurnal cycle in top-of-atmosphere (TOA) fluxes as captured by climate and Earth system models is presented. Observations over the period 2007–2012 made by the Geostationary Earth Radiation Budget (GERB) instrument are used to derive monthly hourly mean outgoing longwave radiation (OLR) and reflected shortwave (RSW) fluxes on a regular 1° latitude–longitude grid covering approximately 60° N–60° S and 60° E–60° W. The impact of missing data is evaluated in detail, and a data-filling solution is implemented using estimates of broadband fluxes from the Spinning Enhanced Visible and Infrared Imager flying on the same Meteosat platform, scaled to the GERB observations. This relatively simple approach is shown to deliver an approximate improvement by a factor of 10 in both the bias caused by missing data and the associated variability in the error. To demonstrate the utility of this V1.1 filled GERB Observations for Climate Model Intercomparison Projects (Obs4MIPs) dataset, comparisons are made to radiative fluxes from two climate configurations of the Hadley Centre's Global Environmental Model: HadGEM3-GC3.1 and HadGEM3-GC5.0. Focusing on marine stratocumulus and deep convective cloud regimes, diurnally resolved comparisons between the models and observations highlight discrepancies between the model configurations in terms of their ability to capture the diurnal amplitude and the phase in TOA fluxes, details that cannot be diagnosed by comparisons at lower temporal resolutions. For these cloud regimes the GC5.0 configuration shows improved fidelity to the observations relative to GC3.1, although notable differences remain. The V1.1 filled GERB Obs4MIPs monthly hourly TOA fluxes are available from the Centre for Environmental Data Analysis, with the OLR fluxes accessible at https://doi.org/10.5285/90148d9b1f1c40f1ac40152957e25467 (Bantges et al., 2023a) and the RSW fluxes accessible at https://doi.org/10.5285/57821b58804945deaf4cdde278563ec2 (Bantges et al., 2023b).

Increasing aerosol optical depth spatial and temporal availability by merging datasets from geostationary and sun-synchronous satellites

Abstract. This comprehensive study analyzed aerosol products from six low-Earth orbit (LEO) and geostationary Earth orbit (GEO) sensors. LEO sensors like the MODerate resolution Imaging Spectroradiometer (MODIS) and VIsible InfraRed Suite (VIIRS) provide one to two daily global measurements, while GEO sensors (Advanced Himawari Imager: AHI, Advanced Baseline Imager: ABI) offer high-frequency data (∼ 10 min) over specific regions. The combination of LEO and GEO capabilities offers expanded coverage of the global aerosol system if aerosol retrievals are applied consistently across all sensors and packaged in an easy-to-use product. The Dark Target aerosol retrieval algorithm was applied to the six sensors, and the resulting Level 2 aerosol optical depth (AOD) products were gridded and merged into a Level 3 quarter-degree latitude–longitude grid with a 30 min temporal resolution, providing the necessary consistency and packaging. Validation of this packaged Level 3 AOD product against Aerosol Robotics NETwork (AERONET) measurements across global locations showcased the merged product's robustness with a correlation coefficient of 0.83, revealing a global mean bias of approximately ±0.05, with 65.5 % of retrievals falling within an expected uncertainty range, underlining the reliability of the dataset. The new gridded Level 3 dataset significantly improved daily global coverage to nearly 45 %, overcoming the limitations of individual sensors, which typically range from 12 % to 25 %. Furthermore, this merged dataset approximates the diurnal cycle of AOD observed by AERONET, thus offering insights into diurnal signatures retrieved elsewhere. The resulting dataset's high spatiotemporal resolution and improved global coverage, especially in regions covered by GEO sensors (Americas and Asia), make it a valuable tool for diverse applications. Tracking aerosol transport from phenomena like wildfires and dust storms is gaining precision, enabling enhanced air quality forecasting and hindcasting. Additionally, the study positions the merged dataset as a significant asset for evaluating and intercomparing regional or global model simulations, which was previously unattainable in such a gridded format. The dataset and fusion framework layout in this study have the potential to include data from recently (future) launched other GEO (FCI, AMI) and LEO (PACE, VIIRS-JPSS) sensors.

Improving runoff simulation in the Western United States with Noah-MP and variable infiltration capacity

Abstract. Streamflow predictions are critical for managing water resources and for environmental conservation, especially in the water-short Western United States. Land surface models (LSMs), such as the variable infiltration capacity (VIC) model and the Noah LSM with multiparameterization options (Noah-MP), play an essential role in providing comprehensive runoff predictions across the region. Virtually all LSMs require parameter estimation (calibration) to optimize their predictive capabilities. Here, we focus on the calibration of VIC and Noah-MP models at a 1/16° latitude–longitude resolution across the Western United States. We first performed global optimal calibration of parameters for both models for 263 river basins in the region. We find that the calibration significantly improves the models' performance, with the median daily streamflow Kling–Gupta efficiency (KGE) increasing from 0.37 to 0.70 for VIC, and from 0.22 to 0.54 for Noah-MP. In general, post-calibration model performance is higher for watersheds with relatively high precipitation and runoff ratios, and at lower elevations. At a second stage, we regionalize the river basin calibrations using the donor-basin method, which establishes transfer relationships for hydrologically similar basins, via which we extend our calibration parameters to 4816 hydrologic unit code (HUC)-10 basins across the region. Using the regionalized parameters, we show that the models' capabilities to simulate high and low flow conditions are substantially improved following calibration and regionalization. The refined parameter sets we developed are intended to support regional hydrological studies and hydrological assessments of climate change impacts.

The study of heat transfers and thermal performance of different types of solar box cookers

Solar fireplaces are important in remote areas with abundant solar radiation, they are a sustainable and environmentally friendly alternative to traditional cooking methods as they do not emit toxic gases. This study aims to experimentally compare solar box cookers of different designs, materials, and features to understand heat transfer and thermal performance to improve overall efficiency. Four different cases with different materials and features of the box structure are studied: Case 1 - non-tinted wooden sides, case 2 - black tinted wooden sides, case 3 - box with glass sides, and Case 4-black tinted wooden sides and coated inside with aluminum foil. Two designs are compared for each case- one with a front flat mirror and one without. All solar fireplaces consist of an inclined glass facing at an angle to the latitude of Baghdad and a base with black fins. The experiments lasted for three months in various weather conditions including cold, hot, dusty, and sunny days in southern Baghdad, Iraq, positioned at Latitude north and longitude East. Factors such as the intensity of incident radiation, wind speed, and ambient air temperature are taken into account during the cooking period. The results indicate that the third glass-sided box achieved the highest thermal efficiency of 93.7% after 120 minutes. The rice was fully cooked in just 97 minutes, the quickest time ever seen with this type of solar cooker, and it had a thermal efficiency of 88%. The fourth box, lined with aluminum foil inside, succeeded the third book with Rice reaching ripeness at 110 minutes with an 80.5% efficiency.

Pembuatan Modul Ajar Peta Online untuk Masyarakat Umum

One of the conveniences on the internet is the existence of online maps, where with online maps, if someone wants to go to an area, they no longer need to look for information by asking other people, but can use an online map called Google Maps. In this community service, a teaching module was created to create online maps with Google My Maps which is expected to help the general public who want to develop map facilities provided by the internet, in this case Google. The method of implementing this community service is planning, analysis, collecting data via the internet (which includes Longitude coordinates, Latitude coordinates, and names of tourist attractions), implementing online map making, and making reports. The data used as a sample is map data of tourist attractions in Pacitan Regency. The result of this community service is a teaching module or activity report that can be used to develop map facilities provided by the internet, in this case Google.

BiSAMNet: A Novel Approach in Maritime Data Completion Using Deep Learning and NLP Techniques

In the extensive monitoring of maritime traffic, maritime management frequently encounters incomplete automatic identification system (AIS) data. This deficiency poses significant challenges to safety management, requiring effective methods to infer corresponding ship information. We tackle this issue using a classification approach. Due to the absence of a fixed road network at sea unlike on land, raw trajectories are difficult to convert and cannot be directly fed into neural networks. We devised a latitude–longitude gridding encoding strategy capable of transforming continuous latitude–longitude data into discrete grid points. Simultaneously, we employed a compression algorithm to further extract significant grid points, thereby shortening the encoding sequence. Utilizing natural language processing techniques, we integrate the Word2vec word embedding approach with our novel biLSTM self-attention chunk-max pooling net (biSAMNet) model, enhancing the classification of vessel trajectories. This method classifies targets into ship types and ship lengths within static information. Employing the Taiwan Strait as a case study and benchmarking against CNN, RNN, and methods based on the attention mechanism, our findings underscore our model’s superiority. The biSAMNet achieves an impressive trajectory classification F1 score of 0.94 in the ship category dataset using only five-dimensional word embeddings. Additionally, through ablation experiments, the effectiveness of the Word2vec pre-trained embedding layer is highlighted. This study introduces a novel method for handling ship trajectory data, addressing the challenge of obtaining ship static information when AIS data are unreliable.

Sightings of dwarf minke whales in the Southern Hemisphere during the SOWER cruises

This paper examines sightings of dwarf minke whales during the SOWER cruises. A total of 12 sightings were made between 1994/95 and 2003/04, across a relatively wide latitude (37°S–62°S) but limited longitude, between IWC Management Area III (0–70°E) and V (130°E–170°W), with no sightings in Area I (0–60°W) or II (60°W–120°W). Despite this low number of sightings, most were close to the Antarctic Convergence at 58°S–65°S. There may be some seasonality in their southbound migration.

SEISMICITY AND SEISMOTECTONIC STUDY FOR ALTUNKOPRI DAM SITE NORTH IRAQ

A seismicity and seismotectonicstudy for a dam site located on latitude (35˚:48΄ – 35˚:50΄) degree North and longitude (44˚:20΄) degree East was carried out. The surrounding area within a circular area ofradius 100 km was also included to determine the seismic activity.It is found that the area was subjected to 10 historical events prior 1900 year with an intensity ranges (V - IX) degree and the area exposed to about 163 recent earthquakes with Ms=1.1 – 5.9.The maps of epicentral locations, tectonic features and lineaments of the study area were compiled and drawn. Matching was carried out for these three maps and it is found that most of earthquake epicenters coincide with the main structural and tectonic phenomena at the dam site.ISO – intensity map for the dam site was also drawn. It is found that the dam site was located between (5 -6) degree earthquake intensity on MMI Scale

CD-type discretization for sea ice dynamics in FESOM version 2

Abstract. Two recently proposed variants of CD-type discretizations of sea ice dynamics on triangular meshes are implemented in the Finite-VolumE Sea ice–Ocean Model (FESOM version 2). The implementations use the finite element method in spherical geometry with longitude–latitude coordinates. Both are based on the edge-based sea ice velocity vectors but differ in the basis functions used to represent the velocities. The first one uses nonconforming linear (Crouzeix–Raviart) basis functions, and the second one uses continuous linear basis functions on sub-triangles obtained by splitting parent triangles into four smaller triangles. Test simulations are run to show how the performance of the new discretizations compares with the A-grid discretization using linear basis functions. Both CD discretizations are found to simulate a finer structure of linear kinematic features (LKFs). Both show some sensitivity to the representation of scalar fields (sea ice concentration and thickness). Cell-based scalars lead to a finer LKF structure for the first CD discretization, but the vertex-based scalars may be advantageous in the second case.

Air pollution emission inventory using national high-resolution spatial parameters for the Nordic countries and analysis of PM2.5 spatial distribution for road transport and machinery and off-road sectors

Abstract. Air pollution is an important cause of adverse health effects, even in the Nordic countries, which have relatively good air quality. Modelling-based air quality assessment of the health impacts relies on reliable model estimates of ambient air pollution concentrations, which furthermore rely on good-quality spatially resolved emission data. While quantitative emission estimates are the cornerstone of good emission data, description of the spatial distribution of the emissions is especially important for local air quality modelling at high resolution. In this paper we present a new air pollution emission inventory for the Nordic countries with high-resolution spatial allocation (1 km × 1 km) covering the years 1990, 1995, 2000, 2005, 2010, 2012, and 2014. The inventory is available at https://doi.org/10.5281/zenodo.10571094 (Paunu et al., 2023). To study the impact of applying national data and methods to the spatial distribution of the emissions, we compared road transport and machinery and off-road sectors to CAMS-REGv4.2, which used a consistent spatial distribution method throughout Europe for each sector. Road transport is a sector with well-established proxies for spatial distribution, while for the machinery and off-road sector, the choice of proxies is not as straightforward as it includes a variety of different type of vehicles and machines operating in various environments. We found that CAMS-REGv4.2 was able to produce similar spatial patterns to our Nordic inventory for the selected sectors. However, the resolution of our Nordic inventory allows for more detailed impact assessment than CAMS-REGv4.2, which had a resolution of 0.1° × 0.05° (longitude–latitude, roughly 5.5 km × 3.5–6.5 km in the Nordic countries). The EMEP/EEA Guidebook chapter on spatial mapping of emissions has recommendations for the sectoral proxies. Based on our analysis we argue that the guidebook should have separate recommendations for proxies for several sub-categories of the machinery and off-road sectors, instead of including them within broader sectors. We suggest that land use data are the best starting point for proxies for many of the subsectors, and they can be combined with other suitable data to enhance the spatial distribution. For road transport, measured traffic flow data should be utilized where possible, to support modelled data in the proxies.

Using Co-Ordinate Systems in Hedonic Housing Regressions

Hedonic house price studies typically incorporate information about location by including either a set of dummy variables to represent individual locations called “neighborhoods” or by using a set of distance (or travel time) variables to characterize locations in terms of proximity to amenities and dis-amenities. As an alternative to these, relatively recent research advocates a latitude–longitude co-ordinate system for incorporating distance information into hedonic house price regressions. This study shows that many of the claims made in this research, particularly those referencing the elimination or diminution of “biases of coefficients of non-distance variables”, are given the particulars of the Monte Carlo experiments, not possible to investigate. We further show, both analytically and with our simulations, that there is no omitted variable bias present in their simulations because their randomly generated non-distance variable is uncorrelated with any of the other variables used in their regression models.

Northern cod re-establish historical migration patterns linked to capelin: insights from pop-up satellite archival tags

In May 2012–2015, 90 large (85–117 cm) Northern cod ( Gadus morhua) with pop-up satellite archival tags (PSATs) set to release 1 year later were released from offshore spawning aggregations on the northeast Newfoundland shelf. Forty-nine (54%) transmitted or were recovered; 82% migrated inshore and 15% remained offshore (balance predated). Geo-locations were based on release, capture, and surfacing positions, and at tag-recorded depths <50 m, on Kalman-predicted light-based longitudes matched with coastal bathymetry. Migrating fish moved southwestward on average 5° longitude (350 km) and 2° latitude (222 km) to the northeast coast of Newfoundland, southern Labrador, and northern Grand Bank, as historically from similar release points. Migration onset through the Labrador Current (<0 °C) and arrival inshore were correlated with capelin ( Mallotus villosus) peak spawning, inshore duration with capelin, and cod biomass. Both species were delayed a month from historical norms. The probability of a cod remaining inshore after 1 December was 50%, which could impact time-dependent surveys. Fishing exploitation was 6% and predation 5%. Northern cod have re-established historical spatial migration patterns, with capelin a key influence on timing and duration inshore.

Ship- and aircraft-based XCH4 over oceans as a new tool for satellite validation

Abstract. Satellite-based estimations of dry-air column-averaged mixing ratios of methane (XCH4) contribute to a better understanding of changes in CH4 emission sources and variations in its atmospheric growth rates. High accuracy of the satellite measurements is required, and therefore, extensive validation is performed, mainly against the Total Carbon Column Observing Network (TCCON). However, validation opportunities at open-ocean areas outside the coastal regions are sparse. We propose a new approach to assess the accuracy of satellite-derived XCH4 trends and variations. We combine various ship and aircraft observations with the help of atmospheric chemistry models, mainly used for the stratospheric column, to derive observation-based XCH4 (obs. XCH4). Based on our previously developed approach for the application to XCO2, we investigated three different advancements, from a simple approach to more elaborate approaches (approaches 1, 2, and 3), to account for the higher tropospheric and stratospheric variability in CH4 as compared to CO2. Between 2014 and 2018, at 20–40° N of the western Pacific, we discuss the uncertainties in the approaches and the derived obs. XCH4 within 10° by 20° latitude–longitude boxes. Uncertainties were 22 ppb (parts per billion) for approach 1, 20 ppb for approach 2, and 16 ppb for approach 3. We analyzed the consistency with the nearest TCCON stations and found agreement of approach 3 with Saga of 1±12 ppb and -1±11 ppb with Tsukuba for the northern and southern latitude box, respectively. Furthermore, we discuss the impact of the modeled stratospheric column on the derived obs. XCH4 by applying three different models in our approaches. Depending on the models, the difference can be more than 12 ppb (0.6 %), showing the importance for the appropriate choice. We show that our obs. XCH4 dataset accurately captures seasonal variations in CH4 over the ocean. Using different retrievals of the Greenhouse Gases Observing Satellite (GOSAT) from the National Institute for Environmental Studies (NIES), the RemoTeC full-physics retrieval operated at the Netherlands Institute for Space Research (SRON), and the full-physics retrieval of the University of Leicester (UoL-OCFP), we demonstrate the applicability of the dataset for satellite evaluation. The comparison with results of approach 3 revealed that NIES showed a difference of −0.04 ± 13 ppb and strong scatter at 20–30° N, while RemoTeC and OCFP have a rather systematic negative bias of −12.1 ± 8.1 and −10.3 ± 9.6 ppb. Our new approach to derive XCH4 reference datasets over the ocean can contribute to the validation of existing and upcoming satellite missions in future.

Spline Model: A Hydrostatic/Non-Hydrostatic Dynamic Core with Space-Time Second-Order Precision and Its Exact Tests

We present a new explicit quasi-Lagrangian integration scheme with the three-dimensional cubic spline function transform (transform = fitting + interpolation, referred to as the “spline format”) on a spherical quasi-uniform longitude–latitude grid. It is a consistent longitude–latitude grid, and to verify the feasibility, accuracy, convergence, and stability of the spline format interpolation scheme for the upstream point on the longitude–latitude grid, which may map a quasi-uniform longitude–latitude grid, a set of ideal, exact test schemes is adopted, which are recognized and proven to be effective internationally. The equilibrium flow test, cross-polar flow test, and Rossby–Haurwitz wave test are used to illustrate the spline scheme uniformity to the linear scheme and to overcome the over-dense grid in the polar region and the non-singularity of the poles. The cross-polar flow test demonstrates that the geostrophic wind crosses the polar area correctly, including the South Pole and North Pole. A non-hydrostatic, fully compressible dynamic core is used to complete the density flow test, demonstrating the existence of a time-varying reference atmosphere and that the spline format can simulate highly nonlinear fine-scale transient flows. It can be compared for the two results of the density flow test between the solution with the spline format and the benchmark reference solution with the linear format. Based on the findings, the non-hydrostatic dynamic core with the spline format is recommended for adoption. When simulated for the flow over an ideal mountain, through the “topographic gravity wave test”, the bicubic surface terrain and terrain-following height coordinates, time-split integration, and vector discrete decomposition can be derived successfully. These may serve as the foundations for a global, unified spline-format numerical model in the future.

A Long-Time-Step-Permitting Tracer Transport Model on the Regular Latitude–Longitude Grid

A Long-Time-Step-Permitting Tracer Transport Model on the Regular Latitude–Longitude Grid

Spatial distribution of northern shrimp Pandalus eous in the Sea of Japan in relation to the seafloor environment

Abstract To explore relationships between spatial distributions of northern shrimp Pandalus eous and environmental factors along the coastline of Honshu Island in the Sea of Japan, we built delta-type two-step generalized additive models (delta-GAM) based on bottom trawl surveys conducted in 2013–2022. The models provide the first quantitative analysis of the species’ habitat, showing that its distribution is associated with bottom sediment type, depth, slope and topographic position index (TPI) alongside the effects of year and region. From the delta-GAM response plots, species habitat preferences in the Sea of Japan were estimated as follows: seafloor deeper than 283 m; muddy rather than sandy bottoms; gently sloped to flat bottoms (<0.8° in slope); and valleys rather than ridges (TPI < 0.9). These results were reviewed in detail along with previously reported distribution records of northern shrimp. Standardized density (s-density) per fishing grid cell (10′ square latitude–longitude mesh) estimated from the delta-GAM results indicated that this species is widely distributed on the continental slope along the coast of Honshu Island. To test plausibility of the s-density analysis, we compared s-density per fishing grid cell with nominal CPUE (kg per haul) per fishing grid cell based on official logbook data from large offshore trawl fisheries. The two were generally positively correlated by year, and the delta-GAM results were assumed to be fairly robust. Finally, potential fishing grounds were explored based on the delta-GAM results.

Physics-Inspired Adaptions to Low-Parameter Neural Network Weather Forecast Systems

Abstract Recently, there has been a surge of research on data-driven weather forecasting systems, especially applications based on convolutional neural networks (CNNs). These are usually trained on atmospheric data represented on regular latitude–longitude grids, neglecting the curvature of Earth. We assess the benefit of replacing the standard convolution operations with an adapted convolution operation that takes into account the geometry of the underlying data (SphereNet convolution), specifically near the poles. Additionally, we assess the effect of including the information that the two hemispheres of Earth have “flipped” properties—for example, cyclones circulating in opposite directions—into the structure of the network. Both approaches are examples of physics-informed machine learning. The methods are tested on the WeatherBench dataset, at a resolution of ∼1.4°, which is higher than many previous studies on CNNs for weather forecasting. For most lead times up to day +10 for 500-hPa geopotential and 850-hPa temperature, we find that using SphereNet convolution or including hemisphere-specific information individually leads to improvement in forecast skill. Combining the two methods typically gives the highest forecast skill. Our version of SphereNet is implemented flexibly and scales well to high-resolution datasets but is still significantly more expensive than a standard convolution operation. Finally, we analyze cases with high forecast error. These occur mainly in winter and are relatively consistent across different training realizations of the networks, pointing to flow-dependent atmospheric predictability.